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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     구글
    -0.07
     المؤ
    -0.07
     BitSet
    -0.07
    θε
    -0.06
     сіль
    -0.06
     BehaviorSubject
    -0.06
     ổ
    -0.06
    -pol
    -0.06
     sla
    -0.06
    理解
    -0.06
    POSITIVE LOGITS
    _display
    0.07
    ま
    0.07
    THEN
    0.06
    REV
    0.06
     некотор
    0.06
     Classic
    0.06
    opies
    0.06
    ificent
    0.06
    Week
    0.06
    zzo
    0.06
    Act Density 0.016%

    No Known Activations