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

    Neuronpedia

    INDEX
    Explanations

    academic and professional titles

    np_acts-logits-general · gemini-2.5-flash-lite

    Important Considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     A
    0.93
     it
    0.85
    $}
    0.85
     T
    0.83
     K
    0.81
     valt
    0.79
     vilka
    0.76
     Kval
    0.75
     Trang
    0.74
     It
    0.73
    POSITIVE LOGITS
    ի
    0.96
    и
    0.93
    の
    0.89
    ın
    0.86
    ↵
    0.86
    layered
    0.79
    의
    0.79
    ี
    0.78
    ச்
    0.76
     honorary
    0.76
    Act Density 0.350%

    No Known Activations