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

    Neuronpedia

    INDEX
    Explanations

    better

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хол
    -0.08
     그녀는
    -0.07
     reveal
    -0.07
    =("
    -0.07
    erts
    -0.07
    ニュ
    -0.07
     Lodge
    -0.07
     discomfort
    -0.06
    /url
    -0.06
    .raise
    -0.06
    POSITIVE LOGITS
     fresh
    0.07
    ><!--
    0.07
     politically
    0.07
    idl
    0.06
    Probably
    0.06
    Router
    0.06
     devour
    0.06
    zeit
    0.06
    busy
    0.06
     电
    0.06
    Act Density 0.003%

    No Known Activations