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

    Neuronpedia

    INDEX
    Explanations

    years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Residences
    0.80
     sowohl
    0.78
     Physicians
    0.74
     etiam
    0.74
    ayvachi
    0.71
     식품
    0.70
     Textured
    0.69
    𝘇
    0.69
    ologische
    0.68
    itosan
    0.68
    POSITIVE LOGITS
     checking
    0.75
     version
    0.70
     -
    0.70
     =
    0.65
     however
    0.65
     maybe
    0.64
     series
    0.64
    них
    0.64
     afast
    0.63
     terrible
    0.62
    Act Density 0.000%

    No Known Activations