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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wonder
    -0.07
    .config
    -0.06
    Draft
    -0.06
    getChild
    -0.06
    adj
    -0.06
    Very
    -0.06
     perfect
    -0.06
    switch
    -0.06
    /[
    -0.06
    _show
    -0.06
    POSITIVE LOGITS
     ув
    0.07
     uğra
    0.06
    isicing
    0.06
     ší
    0.06
    leground
    0.06
     når
    0.06
     рах
    0.06
    误
    0.06
     fist
    0.06
     charcoal
    0.06
    Act Density 0.003%

    No Known Activations