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

    Neuronpedia

    INDEX
    Explanations

    academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     개인정보
    -0.08
     방송
    -0.08
    .gl
    -0.08
     Reeves
    -0.08
     Rigidbody
    -0.08
     ụzọ
    -0.08
     Volleyball
    -0.08
     投
    -0.08
     വീട
    -0.08
     venda
    -0.08
    POSITIVE LOGITS
    Problem
    0.09
     coined
    0.08
    ügen
    0.08
    Constructor
    0.08
    dal
    0.07
    зат
    0.07
    listed
    0.07
    омина
    0.07
    gain
    0.07
    Skipping
    0.07
    Act Density 0.016%

    No Known Activations