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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้าค
    -0.06
    trie
    -0.06
     ایالات
    -0.06
    €
    -0.06
     Sally
    -0.06
    .Tele
    -0.06
    ець
    -0.06
     Pasadena
    -0.06
    ceb
    -0.06
    ΙΑΣ
    -0.06
    POSITIVE LOGITS
     Mondays
    0.07
     delve
    0.06
    .character
    0.06
     условиях
    0.06
    _Up
    0.06
    (){}↵↵
    0.06
    bens
    0.06
    eksiyon
    0.06
    settings
    0.06
     "").
    0.06
    Act Density 0.000%

    No Known Activations