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

    Neuronpedia

    INDEX
    Explanations

    explaining concepts and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.61
    Color
    0.50
    Set
    0.49
    털
    0.48
    es
    0.48
    rand
    0.48
     Chic
    0.47
    Box
    0.46
    ים
    0.45
    Tim
    0.45
    POSITIVE LOGITS
    ಯಲ್ಲಿ
    0.49
    ्न
    0.48
    ၚ
    0.48
     бою
    0.45
     осві
    0.45
    戽
    0.45
    ੋਰ
    0.44
     บุ
    0.44
     પ
    0.43
     освіти
    0.43
    Act Density 0.001%

    No Known Activations