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

    Neuronpedia

    INDEX
    Explanations

    .pow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .har
    -0.08
     activations
    -0.07
    变
    -0.07
    �
    -0.07
     launcher
    -0.07
     cod
    -0.07
    (Base
    -0.07
     pid
    -0.07
     SAX
    -0.07
    .as
    -0.07
    POSITIVE LOGITS
     Pistol
    0.08
    .stopPropagation
    0.08
     кнопк
    0.07
    ⤢
    0.07
    슙
    0.07
    ⒫
    0.07
    🧔
    0.07
    𐤔
    0.07
     использ
    0.07
    蔃
    0.06
    Act Density 0.008%

    No Known Activations