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

    Neuronpedia

    INDEX
    Explanations

    unknown, speculation exists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     understandable
    0.40
     jossa
    0.39
    кта
    0.39
    ffineTransform
    0.39
     sadde
    0.38
    灵魂
    0.38
    Fade
    0.38
     जिसके
    0.37
     በሽታ
    0.37
     sata
    0.36
    POSITIVE LOGITS
     অফ
    0.41
     AVENUE
    0.39
     Learn
    0.38
    using
    0.38
     Among
    0.37
    discord
    0.37
     Autodesk
    0.37
     Amongst
    0.37
     ইউটিউ
    0.37
    among
    0.37
    Act Density 0.000%

    No Known Activations