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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iare
    -0.07
    dex
    -0.07
    下来的
    -0.07
    方式进行
    -0.07
    𝑥
    -0.07
    ài
    -0.06
    lain
    -0.06
     Premiership
    -0.06
     consequence
    -0.06
    strftime
    -0.06
    POSITIVE LOGITS
    _alignment
    0.07
     Invalidate
    0.07
    🎟
    0.07
    _BOTTOM
    0.07
     locking
    0.07
    _DISABLE
    0.07
     userAgent
    0.07
     swept
    0.07
     Echo
    0.07
     "..
    0.07
    Act Density 0.065%

    No Known Activations