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

    Neuronpedia

    INDEX
    Explanations

    harmful acts depicts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    韓国
    0.96
     વૃક્ષ
    0.95
    ا
    0.88
    imizde
    0.87
    institut
    0.86
    𝓶
    0.86
     चोपड़ा
    0.85
    0.85
    但是
    0.84
     Пів
    0.84
    POSITIVE LOGITS
    ,
    0.88
     confluence
    0.77
    ↵↵
    0.77
    <0xC2>
    0.71
     bem
    0.71
     vistas
    0.71
     popularized
    0.70
     conversations
    0.70
     informational
    0.70
     Ske
    0.69
    Act Density 0.000%

    No Known Activations