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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sk
    -0.06
     railing
    -0.06
    	attack
    -0.06
     -------------------------------------------------------------------------
    -0.06
     men
    -0.06
     표시
    -0.06
    ifold
    -0.06
     pastor
    -0.06
    имо
    -0.06
    .categories
    -0.05
    POSITIVE LOGITS
    说话
    0.07
     FontWeight
    0.07
     Quart
    0.07
     gitti
    0.07
     Aug
    0.07
    apanese
    0.07
    notated
    0.07
    .dequeueReusableCell
    0.07
    PED
    0.06
    ERRUPT
    0.06
    Act Density 0.002%

    No Known Activations