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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    исленность
    -0.53
    водство
    -0.52
    oxane
    -0.51
    fone
    -0.50
    télé
    -0.50
     télé
    -0.50
    LUM
    -0.49
    tele
    -0.49
    locker
    -0.49
    loom
    -0.49
    POSITIVE LOGITS
    $_['
    0.66
    تقاوى
    0.54
    resave
    0.51
     kasarigan
    0.48
     autorytatywna
    0.48
    ]")]
    0.48
     Seven
    0.47
    CPtr
    0.47
    InjectAttribute
    0.47
    جوايز
    0.46
    Act Density 0.000%

    No Known Activations