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

    Neuronpedia

    INDEX
    Explanations

    edeutung

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.98
    क
    1.48
    ase
    1.40
    ations
    1.38
    ans
    1.36
    L
    1.34
    k
    1.31
    ”
    1.28
    th
    1.27
    ies
    1.26
    POSITIVE LOGITS
    ה
    1.39
     întâ
    1.16
     îmb
    1.13
    ла
    1.12
     عليه
    1.10
     modificación
    1.09
     ناحيه
    1.09
     funzionalità
    1.06
     duž
    1.04
     chronically
    1.03
    Act Density 0.000%

    No Known Activations