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

    Neuronpedia

    INDEX
    Explanations

    Suites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -video
    -0.07
     AccessToken
    -0.07
    .addComponent
    -0.07
    (fp
    -0.07
    hidden
    -0.07
    _strike
    -0.06
     такого
    -0.06
     Diss
    -0.06
    咨询
    -0.06
    makers
    -0.06
    POSITIVE LOGITS
     Ce
    0.07
     Eph
    0.07
     CharSet
    0.06
    PH
    0.06
     suit
    0.06
     puede
    0.06
    	min
    0.06
    tah
    0.06
    Rib
    0.06
    -Clause
    0.06
    Act Density 0.000%

    No Known Activations