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

    Neuronpedia

    INDEX
    Explanations

    Board or Committee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "With
    -0.07
    _contains
    -0.06
     translucent
    -0.06
     cha
    -0.06
     sé
    -0.06
     opposite
    -0.06
    .idx
    -0.06
    todos
    -0.06
    řej
    -0.06
     Toggle
    -0.06
    POSITIVE LOGITS
    MENU
    0.06
     Sabb
    0.06
     waged
    0.06
     slashed
    0.06
     Sistem
    0.06
    戒
    0.06
     Apostle
    0.06
    _already
    0.06
     وسلم
    0.06
     NUITKA
    0.06
    Act Density 0.003%

    No Known Activations