Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    language related to negotiations and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following auxiliary verbs and commas

    np_acts-logits-general · gemini-2.0-flash

    renovation, remodeling, transformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.63
     المعيارى
    -0.55
     oprot
    -0.52
    Personensuche
    -0.50
    Portail
    -0.49
     memorized
    -0.48
     håll
    -0.48
     pajero
    -0.48
    NOPQRST
    -0.47
    InteropServices
    -0.46
    POSITIVE LOGITS
    改造
    0.86
     rehabilitation
    0.76
     rehabilit
    0.75
     refurb
    0.71
     Rehabilitation
    0.70
     Transformation
    0.69
     remode
    0.69
     remodeling
    0.69
     renovation
    0.69
     rehabilitate
    0.69
    Act Density 0.269%

    No Known Activations