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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    752
    -0.07
    _calls
    -0.06
    _dicts
    -0.06
    _dict
    -0.06
     worthy
    -0.06
    rowave
    -0.06
     pueden
    -0.06
    _regex
    -0.06
     Metrics
    -0.06
     volunteer
    -0.06
    POSITIVE LOGITS
     відпов
    0.07
     Impossible
    0.07
    LETTE
    0.07
    خصص
    0.06
    φορ
    0.06
    INED
    0.06
    SIM
    0.06
    Titulo
    0.06
    CLOSE
    0.06
    >a
    0.06
    Act Density 0.068%

    No Known Activations