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

    Neuronpedia

    INDEX
    Explanations

    instances of personal interactions and expressions of joy or happiness

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

    interrogative or exclamatory words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JsonInclude
    -0.51
    الحياه
    -0.51
    новниш
    -0.50
    ffions
    -0.50
     Reſ
    -0.47
    Initializable
    -0.47
    othelioma
    -0.46
    ValueStyle
    -0.46
    脚注の使い方
    -0.45
     Conſ
    -0.44
    POSITIVE LOGITS
     wearing
    0.36
     Himo
    0.35
     greeted
    0.35
    TextAppearance
    0.35
    ↹
    0.34
    principalColumn
    0.32
    Wearing
    0.32
    ⮕
    0.31
     dressed
    0.31
    Timed
    0.31
    Act Density 0.028%

    No Known Activations