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

    Neuronpedia

    INDEX
    Explanations

    together

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    성을
    -0.07
     QDateTime
    -0.07
     predatory
    -0.06
     Oman
    -0.06
    旅
    -0.06
    ]-'
    -0.06
     Qatar
    -0.06
     ejaculation
    -0.06
    _InternalArray
    -0.06
    τικός
    -0.06
    POSITIVE LOGITS
    FD
    0.06
     afraid
    0.06
    cribed
    0.06
    istically
    0.06
     []:↵
    0.06
    273
    0.06
    AUTH
    0.06
    leine
    0.06
    CM
    0.06
    familia
    0.06
    Act Density 0.011%

    No Known Activations