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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    嗑
    -0.07
     IQ
    -0.07
    AppState
    -0.07
    智商
    -0.07
    _hub
    -0.07
    胳膊
    -0.07
    เย
    -0.07
    PIC
    -0.07
    惊艳
    -0.07
    赝
    -0.06
    POSITIVE LOGITS
     ");
↵
    0.07
    Port
    0.07
    "}↵↵
    0.07
    Ã
    0.07
     Waste
    0.07
    _passed
    0.07
    ,:
    0.07
     \$
    0.06
     Wiley
    0.06
     waypoints
    0.06
    Act Density 0.000%

    No Known Activations