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

    Neuronpedia

    INDEX
    Explanations

    closed won, time units, stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Acknowledgments
    0.69
    Equivalent
    0.67
    陋
    0.66
     പുറ
    0.65
     आईसीआर
    0.65
    Υ
    0.65
    Least
    0.64
     Artur
    0.62
    radial
    0.62
    Razor
    0.62
    POSITIVE LOGITS
     cola
    0.77
     maxHeight
    0.71
     Scandinavia
    0.71
     renovation
    0.69
    abung
    0.68
    дж
    0.66
     landslide
    0.66
     Incluso
    0.66
    ptives
    0.66
    cola
    0.66
    Act Density 0.000%

    No Known Activations