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

    Neuronpedia

    INDEX
    Explanations

    code snippets and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зе
    0.45
     coffee
    0.44
     simulated
    0.44
     Coffee
    0.43
     privacy
    0.43
    ફ
    0.42
     helpful
    0.41
     SOD
    0.41
    šk
    0.41
     cabinet
    0.39
    POSITIVE LOGITS
     忄
    0.54
     గుర్తు
    0.49
    '&
    0.49
     नॉट
    0.48
     shouldn
    0.46
    靂
    0.46
     الانتق
    0.45
     каз
    0.44
     هذ
    0.44
     Elkus
    0.43
    Act Density 0.000%

    No Known Activations