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

    Neuronpedia

    INDEX
    Explanations

    vat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    strength
    -0.07
    |string
    -0.07
     יכולה
    -0.07
    穩定
    -0.07
    Ⓞ
    -0.07
    <main
    -0.07
    fmt
    -0.07
    stable
    -0.06
     lässt
    -0.06
     STREET
    -0.06
    POSITIVE LOGITS
    редел
    0.07
     unbelie
    0.07
     ":
    0.07
    굠
    0.07
     demonstration
    0.07
     enemy
    0.07
    ossil
    0.07
     AttributeSet
    0.07
     invaded
    0.06
     VM
    0.06
    Act Density 0.000%

    No Known Activations