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

    Neuronpedia

    INDEX
    Explanations

    Cognitive biases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Giá
    -0.07
    uppen
    -0.07
    ZERO
    -0.07
    ae
    -0.06
    ść
    -0.06
    σφ
    -0.06
     Latvia
    -0.06
    :max
    -0.06
    „A
    -0.06
    ость
    -0.06
    POSITIVE LOGITS
    _STATUS
    0.06
     cycl
    0.06
    UAGE
    0.06
    _producto
    0.06
    elerik
    0.06
    .nav
    0.06
     cigaret
    0.06
     quiz
    0.06
    齐
    0.06
    ValuePair
    0.06
    Act Density 0.014%

    No Known Activations