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

    Neuronpedia

    INDEX
    Explanations

    programming symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Funktion
    -0.07
     І
    -0.07
     volcanic
    -0.06
     Increment
    -0.06
     Creed
    -0.06
     поход
    -0.06
     Bust
    -0.06
     campaigns
    -0.06
    сього
    -0.06
    .Build
    -0.06
    POSITIVE LOGITS
     ham
    0.08
    tmpl
    0.06
    (Settings
    0.06
     lie
    0.06
    십
    0.06
    状態
    0.06
     дли
    0.06
    .cb
    0.06
     (::
    0.06
     hay
    0.06
    Act Density 0.008%

    No Known Activations