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

    Neuronpedia

    INDEX
    Explanations

    Israel-Hamas conflict and war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ะ
    0.80
    ?)
    0.74
     renormalized
    0.73
    ่า
    0.71
     Saddam
    0.70
     nella
    0.68
     অনুগ্রহ
    0.68
    েরও
    0.68
     randomNumber
    0.67
    _)
    0.65
    POSITIVE LOGITS
    م
    1.02
    ل
    0.93
    I
    0.91
    ق
    0.89
    ص
    0.84
    ور
    0.84
    "
    0.83
    و
    0.82
    К
    0.80
    ли
    0.79
    Act Density 0.000%

    No Known Activations