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

    Neuronpedia

    INDEX
    Explanations

    master

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    要
    -0.07
     куб
    -0.07
    .objects
    -0.07
     fundamental
    -0.07
     office
    -0.07
    _choices
    -0.07
    domain
    -0.06
    animate
    -0.06
    (dot
    -0.06
    ulative
    -0.06
    POSITIVE LOGITS
     JNIEnv
    0.07
    @end
    0.07
    CurrentValue
    0.07
    .'</
    0.07
    sein
    0.07
    .visitMethodInsn
    0.06
     겁
    0.06
     rested
    0.06
     UIAlert
    0.06
     <>
    0.06
    Act Density 0.007%

    No Known Activations