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

    Neuronpedia

    INDEX
    Explanations

    technical jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     creation
    -0.08
    旗
    -0.07
    ogh
    -0.07
    kus
    -0.07
     refugee
    -0.07
    -0.07
     작품
    -0.07
    匙
    -0.07
     사건
    -0.07
    ọn
    -0.07
    POSITIVE LOGITS
    [
    0.09
    /Core
    0.08
    >').
    0.07
    Throwable
    0.07
     stepper
    0.07
    _CAT
    0.07
    _BASIC
    0.07
    '];
    0.07
    _LAYER
    0.07
     vocab
    0.07
    Act Density 0.012%

    No Known Activations