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

    Neuronpedia

    INDEX
    Explanations

    Javascript code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,.
    -0.07
    _config
    -0.07
    ificantly
    -0.07
    .story
    -0.07
    PMC
    -0.07
    ewith
    -0.06
    .=
    -0.06
    ger
    -0.06
    лишком
    -0.06
    سوب
    -0.06
    POSITIVE LOGITS
     avg
    0.07
     vow
    0.06
    UNCH
    0.06
    тах
    0.06
     ав
    0.06
    jte
    0.06
    rips
    0.06
     breakfast
    0.06
     jsx
    0.06
     doma
    0.06
    Act Density 0.000%

    No Known Activations