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

    Neuronpedia

    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dig
    -0.08
    まれ
    -0.07
     Tomb
    -0.07
    mittel
    -0.07
    mage
    -0.07
    臆
    -0.07
     phoenix
    -0.07
    渰
    -0.06
     allele
    -0.06
    계
    -0.06
    POSITIVE LOGITS
    _PROTOCOL
    0.08
    _lbl
    0.07
    MATRIX
    0.07
    吵架
    0.07
     Rating
    0.07
     ))
    0.07
    ยก
    0.07
     등의
    0.07
    ᄃ
    0.06
     Idol
    0.06
    Act Density 0.002%

    No Known Activations