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

    Neuronpedia

    INDEX
    Explanations

    figure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ot
    -0.07
    Fraction
    -0.06
     Elon
    -0.06
    диви
    -0.06
    olis
    -0.06
    ç
    -0.06
     один
    -0.06
     rivalry
    -0.06
     thang
    -0.06
    _POST
    -0.06
    POSITIVE LOGITS
    #plt
    0.06
    /screen
    0.06
    /V
    0.06
    	re
    0.06
    /em
    0.06
    (to
    0.06
    nul
    0.06
    NavigationView
    0.06
    (fr
    0.06
     ป
    0.06
    Act Density 0.169%

    No Known Activations