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

    Neuronpedia

    INDEX
    Explanations

    numbers with units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тельно
    0.42
    izzo
    0.40
    ніше
    0.40
     неиз
    0.38
    inguém
    0.38
     Wasserstein
    0.38
    मै
    0.37
    і
    0.37
     Dexter
    0.36
    enziale
    0.36
    POSITIVE LOGITS
    Arrows
    0.47
    Ways
    0.46
    ാലും
    0.46
    াদনের
    0.46
    BIUM
    0.46
    Ey
    0.45
     ዓይ
    0.45
    ፈለ
    0.45
    Zi
    0.45
    Layer
    0.44
    Act Density 0.039%

    No Known Activations