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

    Neuronpedia

    INDEX
    Explanations

    bitch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esda
    -0.07
     workflow
    -0.06
    スタ
    -0.06
     جی
    -0.06
    reu
    -0.06
    Policy
    -0.06
     Hulu
    -0.06
    거나
    -0.06
    706
    -0.06
    렌
    -0.06
    POSITIVE LOGITS
     bitch
    0.07
    active
    0.07
     ATT
    0.07
    ,img
    0.07
    	Dictionary
    0.07
    leneck
    0.07
    ,out
    0.07
    .getInput
    0.06
     تسم
    0.06
     radiant
    0.06
    Act Density 0.001%

    No Known Activations