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

    Neuronpedia

    INDEX
    Explanations

    mentions of advancements and their novel nature

    oai_token-act-pair · gemini-2.0-flash

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.44
    Geplaatst
    -0.98
     itſelf
    -0.96
     Monfieur
    -0.93
     noDo
    -0.83
     myſelf
    -0.83
     preſent
    -0.81
     Мексичка
    -0.79
     raiſ
    -0.79
     Majefty
    -0.78
    POSITIVE LOGITS
     everyone
    0.60
     some
    0.57
     B
    0.56
     C
    0.56
     all
    0.55
     multi
    0.55
     obcí
    0.52
     O
    0.51
     a
    0.51
    ⎩
    0.50
    Act Density 0.421%

    No Known Activations