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

    Neuronpedia

    INDEX
    Explanations

    choice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _different
    -0.07
     دين
    -0.06
     Set
    -0.06
    simd
    -0.06
    -0.06
    Real
    -0.06
     golf
    -0.06
    ossa
    -0.06
     FALL
    -0.06
    егда
    -0.06
    POSITIVE LOGITS
     vitae
    0.07
    _PROC
    0.07
     quyền
    0.06
    गल
    0.06
     Зак
    0.06
    efore
    0.06
     vents
    0.06
    angled
    0.06
    ]$
    0.06
    ;")↵
    0.06
    Act Density 0.035%

    No Known Activations