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

    Neuronpedia

    INDEX
    Explanations

    properties and features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     redundancy
    -0.07
     PROGRAM
    -0.07
     دم
    -0.07
     EDGE
    -0.07
     Transparent
    -0.06
     rotated
    -0.06
    .Project
    -0.06
     отправ
    -0.06
     accomplishment
    -0.06
     contracting
    -0.06
    POSITIVE LOGITS
     पश
    0.06
    箱
    0.06
    .sdk
    0.06
    πος
    0.06
    !!!
    0.06
     olmuş
    0.05
    inic
    0.05
    浪
    0.05
    _slug
    0.05
    決
    0.05
    Act Density 0.148%

    No Known Activations