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

    Neuronpedia

    INDEX
    Explanations

    chemical suffixes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.42
    eine
    0.37
    e
    0.37
    t
    0.32
    しかし
    0.32
    effect
    0.31
    ein
    0.31
    ↵↵
    0.31
    element
    0.31
    social
    0.31
    POSITIVE LOGITS
    ども
    0.35
    itories
    0.33
     Verfügung
    0.33
     使っ
    0.32
    روع
    0.32
    ISIONS
    0.32
    δήποτε
    0.32
    ின்றன
    0.31
    ítés
    0.31
    AMPLES
    0.31
    Act Density 4.777%

    No Known Activations