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

    Neuronpedia

    INDEX
    Explanations

    richt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     /(
    -0.06
    усти
    -0.06
    _$
    -0.06
     watcher
    -0.06
    268
    -0.06
    332
    -0.06
    -0.06
    .Contains
    -0.06
    \t
    -0.06
    ★★
    -0.06
    POSITIVE LOGITS
    лід
    0.07
     fseek
    0.07
    brit
    0.07
     Exhaust
    0.07
    .modified
    0.07
    rieb
    0.07
    ське
    0.07
    rie
    0.06
     Riding
    0.06
     jue
    0.06
    Act Density 0.007%

    No Known Activations