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

    Neuronpedia

    INDEX
    Explanations

    public health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    等特点
    -0.08
    ushing
    -0.08
    ifice
    -0.07
    ﭼ
    -0.07
    疝
    -0.07
    ;charset
    -0.07
    handleChange
    -0.07
    stile
    -0.07
    /input
    -0.07
     Classification
    -0.07
    POSITIVE LOGITS
     Balls
    0.07
     Links
    0.07
     parameters
    0.07
     NS
    0.07
    _TR
    0.06
    fold
    0.06
     основ
    0.06
     terminator
    0.06
    رح
    0.06
    NS
    0.06
    Act Density 0.270%

    No Known Activations