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

    Neuronpedia

    INDEX
    Explanations

    signature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peaks
    -0.07
    AMY
    -0.07
    анти
    -0.06
    aised
    -0.06
    Better
    -0.06
    KNOWN
    -0.06
    ennis
    -0.06
     Better
    -0.06
     myster
    -0.06
    gaben
    -0.06
    POSITIVE LOGITS
     accusation
    0.08
    <footer
    0.06
     вий
    0.06
    固
    0.06
     издел
    0.06
     toolStrip
    0.06
     Settlement
    0.06
    .parents
    0.06
     食
    0.06
    _alarm
    0.06
    Act Density 0.007%

    No Known Activations