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

    Neuronpedia

    INDEX
    Explanations

    expressing opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TAIL
    -0.06
    19
    -0.06
    _sys
    -0.06
    _ot
    -0.06
    Locker
    -0.06
    (song
    -0.06
    -tm
    -0.06
     원
    -0.06
     scarce
    -0.06
     ста
    -0.06
    POSITIVE LOGITS
     latest
    0.07
    .fromCharCode
    0.07
     пару
    0.06
    .contentMode
    0.06
     strengthening
    0.06
     ارسال
    0.06
    (Enum
    0.06
     resett
    0.06
     toll
    0.06
     」
    0.06
    Act Density 0.046%

    No Known Activations