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

    Neuronpedia

    INDEX
    Explanations

    sweet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FHA
    -0.07
    TXT
    -0.07
     c
    -0.07
    alloca
    -0.06
    *a
    -0.06
     Cer
    -0.06
    Row
    -0.06
    UseProgram
    -0.06
    ‌شوند
    -0.06
     echoing
    -0.06
    POSITIVE LOGITS
    151
    0.08
    _PY
    0.07
    iss
    0.07
     мот
    0.06
     diret
    0.06
     Sabb
    0.06
    .son
    0.06
    ]];↵↵
    0.06
    _DI
    0.06
     Knight
    0.06
    Act Density 0.004%

    No Known Activations