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

    Neuronpedia

    INDEX
    Explanations

    survival and labor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -resource
    -0.07
    agine
    -0.07
     extracts
    -0.06
    ri
    -0.06
     wounded
    -0.06
     striped
    -0.06
    pee
    -0.06
    .streaming
    -0.06
    Fuck
    -0.06
    殊
    -0.06
    POSITIVE LOGITS
    <Scalars
    0.06
    unicipio
    0.06
     recession
    0.06
     lanz
    0.06
    _author
    0.06
     vendor
    0.06
     커
    0.06
     norske
    0.06
     dolor
    0.06
     Václav
    0.06
    Act Density 0.168%

    No Known Activations