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

    Neuronpedia

    INDEX
    Explanations

    adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .parse
    -0.07
    (sql
    -0.07
    -reaching
    -0.07
     printf
    -0.07
    ida
    -0.06
     inclusion
    -0.06
     contar
    -0.06
     thru
    -0.06
    ворення
    -0.06
     towards
    -0.06
    POSITIVE LOGITS
     typically
    0.07
     легко
    0.06
     修
    0.06
    .Company
    0.06
    _IDENT
    0.06
     geil
    0.06
     strategically
    0.06
    ",(
    0.06
    (milliseconds
    0.06
     ổ
    0.06
    Act Density 0.151%

    No Known Activations