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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gregar
    -0.08
    анов
    -0.07
    LEEP
    -0.07
     округ
    -0.07
     Δια
    -0.06
    inally
    -0.06
    quiring
    -0.06
    يكا
    -0.06
    encing
    -0.06
    idual
    -0.06
    POSITIVE LOGITS
    (tbl
    0.07
    _DIAG
    0.07
    _species
    0.06
     workings
    0.06
     каф
    0.06
     tav
    0.06
     japan
    0.06
     Fry
    0.06
    _bug
    0.06
    �
    0.06
    Act Density 0.051%

    No Known Activations