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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _feats
    -0.07
    _FINISH
    -0.07
     vess
    -0.07
    -regexp
    -0.06
     المغ
    -0.06
    -du
    -0.06
    (validate
    -0.06
    _dual
    -0.06
    ();?>
    -0.06
    /boot
    -0.06
    POSITIVE LOGITS
     Counseling
    0.06
    .sdk
    0.06
     Stefan
    0.06
    insurance
    0.06
    инг
    0.06
     Anita
    0.06
    .stack
    0.06
    owa
    0.06
     되었다
    0.05
    แนะนำ
    0.05
    Act Density 0.002%

    No Known Activations