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

    Neuronpedia

    INDEX
    Explanations

    believing in yourself and your value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (~
    0.96
     (...
    0.91
     ($
    0.87
     (
    0.83
     sorts
    0.82
    ($
    0.80
    （
    0.80
    ...(
    0.79
     via
    0.77
    …
    0.76
    POSITIVE LOGITS
     omdat
    0.73
     Dc
    0.71
     বরা
    0.69
     pourcentage
    0.68
     SMI
    0.68
     Inspirational
    0.66
     integrado
    0.65
     Attitude
    0.65
     Inte
    0.65
     believing
    0.63
    Act Density 0.111%

    No Known Activations