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

    Neuronpedia

    INDEX
    Explanations

    Equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pumpkin
    -0.10
     cierta
    -0.08
    Bent
    -0.08
     Hex
    -0.08
    پا
    -0.08
    Home
    -0.07
     Wave
    -0.07
     prefab
    -0.07
     वैश
    -0.07
    าป
    -0.07
    POSITIVE LOGITS
     이렇게
    0.08
     Таким
    0.08
    ^^
    0.08
    Таким
    0.08
     மேலும்
    0.07
    aside
    0.07
     என்று
    0.07
    buttons
    0.07
     கழ
    0.07
    olare
    0.07
    Act Density 0.185%

    No Known Activations