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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     healthy
    -0.07
    Sorry
    -0.06
    	cursor
    -0.06
     enrollment
    -0.06
     sequential
    -0.06
     Semiconductor
    -0.06
     Drinking
    -0.06
     Thanks
    -0.06
     drinks
    -0.06
     Composer
    -0.06
    POSITIVE LOGITS
    UIColor
    0.06
    اصر
    0.06
    _auc
    0.06
     Alto
    0.06
     noh
    0.06
    _Comm
    0.06
    ullo
    0.06
     RTP
    0.06
     slab
    0.06
     분야
    0.06
    Act Density 0.068%

    No Known Activations