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

    Neuronpedia

    INDEX
    Explanations

    how to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝓈
    0.85
    ABASE
    0.77
    citing
    0.75
     ஆங்கில
    0.74
    英語版
    0.73
     細胞
    0.73
     Dernière
    0.73
     accedere
    0.73
    𝒸
    0.72
    ஆ
    0.71
    POSITIVE LOGITS
    rema
    0.70
    RootDir
    0.69
    osu
    0.68
     unmatched
    0.68
    osen
    0.67
     firmas
    0.66
     Hyper
    0.66
     సహ
    0.66
    ilt
    0.66
    kapet
    0.65
    Act Density 0.001%

    No Known Activations