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

    Neuronpedia

    INDEX
    Explanations

    Risk Assessment and categorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    펄
    0.69
    त्ते
    0.69
     potencialmente
    0.67
     Dispon
    0.67
     अपेक्षाकृत
    0.66
    QUID
    0.66
     тру
    0.65
     Alley
    0.65
    灘
    0.65
    ܐ
    0.65
    POSITIVE LOGITS
     him
    0.69
     एससी
    0.66
     her
    0.65
    给她
    0.65
     reviewing
    0.60
     Chez
    0.60
    ble
    0.59
     tools
    0.58
     Miss
    0.58
     cameras
    0.58
    Act Density 0.001%

    No Known Activations