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

    Neuronpedia

    INDEX
    Explanations

    calculating sequences with prior values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .gz
    -0.06
    bedo
    -0.06
     yetiş
    -0.06
    plans
    -0.06
    +h
    -0.06
     �
    -0.06
    bx
    -0.06
    hud
    -0.06
    ILES
    -0.06
    bm
    -0.06
    POSITIVE LOGITS
     narrative
    0.07
    DrawerToggle
    0.07
     hemat
    0.07
     Ama
    0.06
     TypeScript
    0.06
    [target
    0.06
     HC
    0.06
     asserting
    0.06
    /at
    0.06
     включа
    0.06
    Act Density 0.007%

    No Known Activations