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

    Neuronpedia

    INDEX
    Explanations

    English, Devanagari script, and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tó
    0.43
     tracers
    0.41
     elimina
    0.40
    蟲
    0.39
    蟎
    0.39
    եցին
    0.38
    ński
    0.37
     rospy
    0.37
    動畫
    0.37
    ოლ
    0.36
    POSITIVE LOGITS
    HDR
    0.40
     nineteenth
    0.39
    ोरेंट
    0.39
    Render
    0.37
    Star
    0.37
     eighteenth
    0.36
     १८
    0.36
     बदलकर
    0.36
    ۱
    0.36
    𝙈
    0.36
    Act Density 0.001%

    No Known Activations