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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     singles
    -0.07
    taxonomy
    -0.07
     reached
    -0.07
    oxid
    -0.07
     ValueType
    -0.07
    edith
    -0.06
     boredom
    -0.06
    사지
    -0.06
     massacre
    -0.06
    issement
    -0.06
    POSITIVE LOGITS
    Few
    0.06
     girls
    0.06
     MUCH
    0.06
     {{--<
    0.06
    onavir
    0.06
     SP
    0.06
     необхідно
    0.06
    rometer
    0.06
    <G
    0.06
     backButton
    0.06
    Act Density 0.075%

    No Known Activations