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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	target
    -0.07
     文
    -0.07
    _winner
    -0.06
     σκο
    -0.06
     قبل
    -0.06
    inus
    -0.06
    stein
    -0.06
    arten
    -0.06
    उत
    -0.06
    ﾆﾆ
    -0.06
    POSITIVE LOGITS
     ttk
    0.09
     InputDecoration
    0.08
     seasonal
    0.07
     disqualified
    0.07
     Seriously
    0.07
    osate
    0.07
     khoản
    0.06
     Gauss
    0.06
    umbed
    0.06
    hack
    0.06
    Act Density 0.001%

    No Known Activations