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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وسلم
    -0.09
     그는
    -0.07
     RTWF
    -0.06
     الوص
    -0.06
    /simple
    -0.06
     Kou
    -0.06
    ("""
    -0.06
     अध
    -0.06
     olmadığını
    -0.06
    _DH
    -0.06
    POSITIVE LOGITS
    mar
    0.07
    ساس
    0.06
    IF
    0.06
    yne
    0.06
     soup
    0.06
    ric
    0.06
    enthal
    0.06
     kneeling
    0.06
    _mas
    0.06
    MAR
    0.06
    Act Density 0.000%

    No Known Activations