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

    Neuronpedia

    INDEX
    Explanations

    breathing and physical states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     हितों
    0.77
     prostitution
    0.73
     extranjeros
    0.69
    गारी
    0.67
    𝗝
    0.66
    FRINGEMENT
    0.66
     injustices
    0.66
     финанси
    0.65
    Crisis
    0.65
     injustice
    0.65
    POSITIVE LOGITS
    ↵↵
    0.79
     de
    0.70
     with
    0.69
     as
    0.66
     before
    0.63
    不是
    0.63
    {
    0.63
     on
    0.62
     la
    0.61
    ↵
    0.60
    Act Density 0.549%

    No Known Activations