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

    Neuronpedia

    INDEX
    Explanations

    prices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     affirmation
    -0.07
     honestly
    -0.07
     cats
    -0.07
    铱
    -0.07
    红茶
    -0.06
    ishi
    -0.06
     túi
    -0.06
    /address
    -0.06
     ensemble
    -0.06
    斋
    -0.06
    POSITIVE LOGITS
    ━━
    0.08
    ENCHMARK
    0.07
     supervised
    0.07
    /*----------------------------------------------------------------
    0.07
    handleRequest
    0.07
    _DEFINE
    0.07
     TTC
    0.07
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.07
    ;text
    0.07
     terrific
    0.07
    Act Density 0.029%

    No Known Activations