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

    Neuronpedia

    INDEX
    Explanations

    for loops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    кових
    -0.07
     Candle
    -0.07
     horrified
    -0.06
    toi
    -0.06
    ้วย
    -0.06
    gger
    -0.06
    рак
    -0.06
    orig
    -0.06
    sam
    -0.06
     역사
    -0.06
    POSITIVE LOGITS
     CT
    0.07
     Paid
    0.07
    .Msg
    0.07
    PropertyValue
    0.06
    []{↵
    0.06
     Traditional
    0.06
    �
    0.06
    _PM
    0.06
    FunctionFlags
    0.06
    递
    0.06
    Act Density 0.005%

    No Known Activations