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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate action or progress

    oai_token-act-pair · gemini-2.0-flash

    words related to paving the way or facilitating processes

    np_token-act-pair-logits · gpt-4o-mini

    business and finance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.67
     متعلقه
    -0.64
     للمعارف
    -0.55
     zelve
    -0.51
     attaques
    -0.51
     deſt
    -0.51
    véni
    -0.50
     Interests
    -0.50
     ExecuteAsync
    -0.49
    oucí
    -0.48
    POSITIVE LOGITS
    دانشنامهٔ
    0.59
    <bos>
    0.56
     références
    0.52
    soever
    0.51
    Facades
    0.49
    wnież
    0.48
    rall
    0.48
    比较好
    0.48
    логе
    0.47
    MessageInfo
    0.47
    Act Density 2.022%

    No Known Activations