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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (H
    -0.07
    �
    -0.06
     Didn
    -0.06
    /H
    -0.06
    Im
    -0.06
    mania
    -0.06
    557
    -0.06
    çak
    -0.06
     Hut
    -0.06
    Didn
    -0.06
    POSITIVE LOGITS
     Exception
    0.07
    เทศ
    0.07
    getError
    0.07
    IMIZE
    0.07
    гляд
    0.07
    porate
    0.07
    (open
    0.06
    .mkdir
    0.06
    issional
    0.06
     Jacksonville
    0.06
    Act Density 0.387%

    No Known Activations