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

    Neuronpedia

    INDEX
    Explanations

    today

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Icelandic
    -0.07
    一下
    -0.07
     Lap
    -0.07
    슙
    -0.06
     Bourbon
    -0.06
    捐赠
    -0.06
    는데
    -0.06
     cui
    -0.06
    听说
    -0.06
     sonra
    -0.06
    POSITIVE LOGITS
    _particles
    0.08
    ********************************
    0.07
    OLID
    0.07
    "errors
    0.07
     ולה
    0.07
    .weights
    0.07
    registers
    0.07
    _render
    0.07
    Raster
    0.06
     }]
    0.06
    Act Density 0.002%

    No Known Activations