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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or actions taken

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

    verbs followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ustimmung
    -0.45
     organis
    -0.43
     Tap
    -0.40
    ENH
    -0.39
    TagMode
    -0.39
     defaultstate
    -0.39
     UnityEditor
    -0.39
    cillas
    -0.38
    佐
    -0.38
     title
    -0.37
    POSITIVE LOGITS
    出版年
    0.52
     ब्रेकडाउन
    0.52
    0.50
     Taktlose
    0.50
    CreateModel
    0.49
    awtextra
    0.49
     Chwiliwch
    0.48
     AssemblyCulture
    0.47
    ItemBackground
    0.47
     Autorizaciones
    0.47
    Act Density 0.057%

    No Known Activations