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

    Neuronpedia

    INDEX
    Explanations

    configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -mouth
    -0.07
    لال
    -0.07
    >Lorem
    -0.06
     acompan
    -0.06
     σχέ
    -0.06
     spy
    -0.06
     thứ
    -0.06
    arcy
    -0.06
    弥
    -0.06
     Kre
    -0.06
    POSITIVE LOGITS
     enzymes
    0.06
     Defendants
    0.06
     irrespective
    0.06
     ave
    0.06
    Global
    0.06
     deactivate
    0.06
     [...]
    0.06
     mekan
    0.06
    .Submit
    0.06
    Didn
    0.06
    Act Density 0.000%

    No Known Activations