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

    Neuronpedia

    INDEX
    Explanations

    "Hey", "poison", "intelligence", "enjoy", "ok", "exist"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.01
    ון
    0.98
     sentidos
    0.95
     Peterborough
    0.94
     அதை
    0.94
    ら
    0.94
    を購入
    0.92
    vole
    0.91
    我
    0.91
    を紹介
    0.91
    POSITIVE LOGITS
    ς
    1.06
    szer
    1.05
    s
    1.05
    ামুটি
    1.02
    e
    0.95
    1
    0.93
    ERS
    0.93
    <unused557>
    0.92
    ными
    0.90
    ூழ
    0.85
    Act Density 0.152%

    No Known Activations