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

    Neuronpedia

    INDEX
    Explanations

    ($

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Early
    -0.07
    жно
    -0.07
    .into
    -0.06
    ां
    -0.06
     střed
    -0.06
     represented
    -0.06
     […
    -0.06
    adden
    -0.06
    _Menu
    -0.06
    에서
    -0.06
    POSITIVE LOGITS
     haus
    0.07
     právní
    0.07
    ATURE
    0.06
     FOOD
    0.06
     QVBoxLayout
    0.06
    ्टम
    0.06
     фунда
    0.06
     Ав
    0.06
    TEE
    0.06
    ="<?=$
    0.06
    Act Density 0.003%

    No Known Activations