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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Day
    -0.08
    溪
    -0.08
     Duo
    -0.08
    REG
    -0.08
     busty
    -0.08
    :\/\/
    -0.07
    全民健身
    -0.07
     injuries
    -0.07
     servicio
    -0.07
     dung
    -0.07
    POSITIVE LOGITS
    Tel
    0.07
    ToggleButton
    0.07
     październ
    0.07
    )},↵
    0.06
    .Rotate
    0.06
     Alexand
    0.06
     znalazł
    0.06
    significant
    0.06
     GAL
    0.06
    _elements
    0.06
    Act Density 0.034%

    No Known Activations