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

    Neuronpedia

    INDEX
    Explanations

    Early

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Episode
    -0.07
    po
    -0.07
    מ
    -0.07
     altı
    -0.06
     возраста
    -0.06
    /ne
    -0.06
    ย
    -0.06
    Italian
    -0.06
    /e
    -0.06
     Ad
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ."]
    0.07
     Parsons
    0.06
    ARS
    0.06
    ars
    0.06
     Mao
    0.06
    ζα
    0.06
    asar
    0.06
     intake
    0.06
     directors
    0.06
    Act Density 0.008%

    No Known Activations