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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("").
    -0.08
    れて
    -0.06
    _documento
    -0.06
     سفید
    -0.06
     비교
    -0.06
    เคล
    -0.06
    されて
    -0.06
     华
    -0.06
     tox
    -0.06
     Dickens
    -0.06
    POSITIVE LOGITS
     informational
    0.07
    sko
    0.06
    car
    0.06
    τρι
    0.06
    registry
    0.06
     kolej
    0.06
    (hw
    0.06
    experiment
    0.06
     Fox
    0.06
     acct
    0.06
    Act Density 0.019%

    No Known Activations