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

    Neuronpedia

    INDEX
    Explanations

    He

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Touches
    -0.07
    ことに
    -0.06
    Ada
    -0.06
    Oops
    -0.06
     peacefully
    -0.06
     جنسی
    -0.06
     ubuntu
    -0.06
     Mü
    -0.06
     giveaway
    -0.06
    Australia
    -0.06
    POSITIVE LOGITS
    elsen
    0.07
     σύν
    0.07
    gebung
    0.07
    τωση
    0.06
     обмеж
    0.06
    _APPLICATION
    0.06
    .ToolStripSeparator
    0.06
    政府
    0.06
    CRYPT
    0.06
    ansom
    0.06
    Act Density 0.025%

    No Known Activations