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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HWND
    -0.09
    isex
    -0.09
     투
    -0.08
     anteriores
    -0.08
    secut
    -0.08
    _sound
    -0.08
     SOUND
    -0.08
    投
    -0.08
     gate
    -0.08
    �
    -0.07
    POSITIVE LOGITS
    料
    0.13
     Composite
    0.09
     composites
    0.09
     composite
    0.09
     مادة
    0.08
    增强
    0.08
     Compound
    0.08
     verplicht
    0.08
    强化
    0.08
    板
    0.08
    Act Density 0.004%

    No Known Activations