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

    Neuronpedia

    INDEX
    Explanations

    end of quotes or sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻲ
    1.01
    ();}
    0.89
     alot
    0.89
     minha
    0.85
     &/
    0.84
    ();//
    0.83
    または
    0.83
    ']==
    0.83
     bzw
    0.82
     یا
    0.82
    POSITIVE LOGITS
    ↵↵
    0.93
     Despite
    0.90
     Meanwhile
    0.81
    ↵
    0.80
     According
    0.79
    Despite
    0.74
     Nevertheless
    0.73
    According
    0.71
     Apparently
    0.69
     Moreover
    0.66
    Act Density 0.020%

    No Known Activations