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

    Neuronpedia

    INDEX
    Explanations

    pass signal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Definition
    0.84
    اً
    0.83
    Relationship
    0.78
    i
    0.77
    à
    0.77
    p
    0.77
    Description
    0.75
    ير
    0.74
    Calendar
    0.74
    Satisfaction
    0.74
    POSITIVE LOGITS
     pensioners
    0.89
     erythrocytes
    0.87
     photospheres
    0.84
    ल
    0.81
     compromise
    0.79
     kilobytes
    0.79
    🄴
    0.78
    гээ
    0.77
    ಲಾಯಿತು
    0.77
    内核
    0.77
    Act Density 0.000%

    No Known Activations