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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trusted
    -0.06
    ;;;;;;;;
    -0.06
     πρά
    -0.06
     الك
    -0.06
    ης
    -0.06
    Jam
    -0.06
     lái
    -0.06
     zoom
    -0.06
     апп
    -0.06
     ink
    -0.06
    POSITIVE LOGITS
    ">'.
    0.08
     murders
    0.07
    _delete
    0.07
    ニア
    0.07
    mination
    0.07
     nova
    0.07
     employment
    0.07
    >'.
    0.06
    agate
    0.06
    (dom
    0.06
    Act Density 0.000%

    No Known Activations