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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _security
    -0.07
    ve
    -0.07
     Avec
    -0.07
    Representation
    -0.07
    _snd
    -0.07
    _timer
    -0.07
     Candle
    -0.06
    Token
    -0.06
    Digest
    -0.06
     leasing
    -0.06
    POSITIVE LOGITS
    253
    0.07
     Rosenstein
    0.06
    NAMESPACE
    0.06
    ————————
    0.06
     klid
    0.06
    teş
    0.06
     Garten
    0.06
     ري
    0.06
     исп
    0.06
     Destruction
    0.06
    Act Density 0.032%

    No Known Activations