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

    Neuronpedia

    INDEX
    Explanations

    mathematical definitions and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fitting
    1.01
    oxygenase
    0.97
     Outback
    0.94
     Dung
    0.93
     ([]
    0.93
    люс
    0.90
    焜
    0.89
    chaoxing
    0.88
    hall
    0.88
     Ony
    0.88
    POSITIVE LOGITS
    ज
    0.96
     gev
    0.91
     tarz
    0.90
     es
    0.84
    ษา
    0.84
     grap
    0.83
    права
    0.83
    يطان
    0.82
    न
    0.81
     balo
    0.81
    Act Density 0.002%

    No Known Activations