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

    Neuronpedia

    INDEX
    Explanations

    overheard speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    狠
    -0.07
    iska
    -0.07
     rave
    -0.06
    }`}↵
    -0.06
    ランス
    -0.06
     runaway
    -0.06
     Library
    -0.06
     dropdown
    -0.06
     Teen
    -0.06
     covered
    -0.06
    POSITIVE LOGITS
    (dx
    0.06
    _prediction
    0.06
     FORWARD
    0.06
    (dec
    0.06
     minul
    0.06
     craftsm
    0.06
    stm
    0.06
    urrency
    0.06
     Ms
    0.06
    KER
    0.06
    Act Density 0.001%

    No Known Activations