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

    Neuronpedia

    INDEX
    Explanations

    code, technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iếng
    -0.07
    _editor
    -0.06
     spiral
    -0.06
    (Collision
    -0.06
    [array
    -0.06
    γρα
    -0.06
    าษ
    -0.06
    inner
    -0.06
    ys
    -0.06
    ٔ
    -0.06
    POSITIVE LOGITS
     prince
    0.07
     dương
    0.07
    だけど
    0.07
    Prince
    0.06
     ECM
    0.06
     Jeremiah
    0.06
     drown
    0.06
     Germ
    0.06
    Nat
    0.06
    萬
    0.06
    Act Density 0.000%

    No Known Activations