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

    Neuronpedia

    INDEX
    Explanations

    verbs related to modification or adjustment

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

    control or modify parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     العلم
    -0.48
    Accessory
    -0.43
     portal
    -0.42
     Sakai
    -0.41
     Arias
    -0.40
     Nilsson
    -0.38
    accessory
    -0.38
    kadot
    -0.38
     honoured
    -0.37
    PageModule
    -0.37
    POSITIVE LOGITS
     EconPapers
    0.58
     kasarigan
    0.57
     AssemblyCulture
    0.47
    StructEnd
    0.47
    RTCK
    0.46
    Ikus
    0.45
    帖最后由
    0.45
     myſelf
    0.44
    TokenNameLBRACE
    0.43
    __(/*!
    0.42
    Act Density 0.002%

    No Known Activations