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

    Neuronpedia

    INDEX
    Explanations

    ::

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sev
    -0.07
     pand
    -0.06
    Jan
    -0.06
    ْن
    -0.06
    	write
    -0.06
     ～
    -0.06
     shard
    -0.06
     civ
    -0.06
    shake
    -0.06
    _Panel
    -0.06
    POSITIVE LOGITS
    /docs
    0.08
    thern
    0.07
     Trials
    0.07
    lijah
    0.07
     만
    0.06
     supervision
    0.06
    children
    0.06
     unseen
    0.06
     yık
    0.06
    .BooleanField
    0.06
    Act Density 0.005%

    No Known Activations