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

    Neuronpedia

    INDEX
    Explanations

    URL path segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anxiously
    1.01
     Э
    0.95
     Addressing
    0.95
     Lively
    0.92
     addressing
    0.89
     Execute
    0.89
     Buildable
    0.87
     Sufficient
    0.87
     UIAlert
    0.86
     tempering
    0.86
    POSITIVE LOGITS
    CET
    0.77
    {
    0.71
    ுள்ளார்
    0.70
    UTC
    0.69
    tailed
    0.66
    param
    0.65
    Covid
    0.64
    Zn
    0.64
    ]={
    0.64
    Caractéristiques
    0.64
    Act Density 0.000%

    No Known Activations