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

    Neuronpedia

    INDEX
    Explanations

    reviews and explanations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.08
    ennes
    -0.07
     Royals
    -0.07
    uez
    -0.07
    Archivo
    -0.07
     Clearly
    -0.07
     político
    -0.06
    䲢
    -0.06
     ByteString
    -0.06
    rias
    -0.06
    POSITIVE LOGITS
    _shot
    0.08
    .CON
    0.07
    _modes
    0.07
    _states
    0.07
    国际市场
    0.07
    敢于
    0.07
    (tool
    0.07
     encounters
    0.06
    :UI
    0.06
    會
    0.06
    Act Density 0.003%

    No Known Activations