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

    Neuronpedia

    INDEX
    Explanations

    coding errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (parser
    -0.07
    average
    -0.07
    =https
    -0.06
    ací
    -0.06
     faithfully
    -0.06
    901
    -0.06
    domain
    -0.06
     uomo
    -0.06
    ajo
    -0.06
     concentrated
    -0.06
    POSITIVE LOGITS
    ност
    0.06
     nit
    0.06
     Term
    0.06
    ฟ
    0.06
    éri
    0.06
    $errors
    0.06
     NST
    0.06
    .labelControl
    0.06
     Geh
    0.06
    ισ
    0.06
    Act Density 0.068%

    No Known Activations