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

    Neuronpedia

    INDEX
    Explanations

    diegetic sound, trifecta control, Wrangler

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.60
    리
    1.56
    ς
    1.41
    ओं
    1.36
    s
    1.34
    c
    1.30
    an
    1.30
    ים
    1.23
    on
    1.22
    et
    1.18
    POSITIVE LOGITS
    ă
    1.41
     be
    1.01
    ");
    1.00
    েন্ট
    0.98
     arrête
    0.94
    "});
    0.91
     bude
    0.91
     može
    0.88
     elenc
    0.88
    LoggedIn
    0.87
    Act Density 0.000%

    No Known Activations