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

    Neuronpedia

    INDEX
    Explanations

    find commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ză
    0.72
     suppresses
    0.70
     orthogonality
    0.68
     puppy
    0.67
     plumbers
    0.66
     actuation
    0.65
    娀
    0.64
     attendant
    0.64
    TouchEvent
    0.64
     développe
    0.63
    POSITIVE LOGITS
     وفي
    0.92
    IN
    0.91
    爾
    0.90
    ﺭ
    0.89
    ﻭ
    0.84
    ٬
    0.78
    D
    0.77
    瓏
    0.77
    ﺩ
    0.75
     savor
    0.74
    Act Density 0.004%

    No Known Activations