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

    Neuronpedia

    INDEX
    Explanations

    European places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    msg
    -0.06
    Pří
    -0.06
    理
    -0.06
     robes
    -0.06
     Maurice
    -0.06
    Forms
    -0.06
    _moves
    -0.05
    .findall
    -0.05
     místo
    -0.05
    _dataframe
    -0.05
    POSITIVE LOGITS
     영화
    0.07
    ">@
    0.07
    .Screen
    0.07
     вой
    0.07
    .water
    0.07
     свобод
    0.07
    ğını
    0.06
     ransom
    0.06
     Mention
    0.06
     Escape
    0.06
    Act Density 0.008%

    No Known Activations