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

    Neuronpedia

    INDEX
    Explanations

    Historical events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atör
    -0.08
     shader
    -0.08
     oraz
    -0.07
    şi
    -0.07
    ...)↵↵
    -0.06
    ">'↵
    -0.06
    —including
    -0.06
    mtree
    -0.06
    uft
    -0.06
    —even
    -0.06
    POSITIVE LOGITS
     requestOptions
    0.06
    estate
    0.06
    _COMMIT
    0.06
     StringIO
    0.06
    $I
    0.06
     thức
    0.06
    dx
    0.06
     Karen
    0.06
    イ
    0.06
    Pokemon
    0.06
    Act Density 0.017%

    No Known Activations