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

    Neuronpedia

    INDEX
    Explanations

    General English sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cramped
    -0.07
     <>
    -0.07
     Kardash
    -0.07
    (big
    -0.07
    —that
    -0.06
     certifications
    -0.06
     trov
    -0.06
    Fair
    -0.06
    .jp
    -0.06
     dair
    -0.06
    POSITIVE LOGITS
    ئة
    0.06
    _agg
    0.06
     informations
    0.06
    .PERMISSION
    0.06
    LECT
    0.06
     takson
    0.06
    _xml
    0.06
    르게
    0.06
     secretion
    0.06
     Eid
    0.06
    Act Density 0.027%

    No Known Activations