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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    声を
    -0.07
     notice
    -0.07
     officers
    -0.07
     použít
    -0.07
     kancel
    -0.07
     Vác
    -0.06
     gbc
    -0.06
    她
    -0.06
    Segoe
    -0.06
     digest
    -0.06
    POSITIVE LOGITS
    Nil
    0.07
    シア
    0.06
    386
    0.06
    zione
    0.06
    ertia
    0.06
    ereal
    0.06
     Bucc
    0.06
    execution
    0.06
    $category
    0.06
     öyle
    0.06
    Act Density 0.000%

    No Known Activations