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

    Neuronpedia

    INDEX
    Explanations

    overhang

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neder
    0.87
     TextAppearance
    0.86
     그런데
    0.83
     unload
    0.79
    ي
    0.78
    Л
    0.78
    vgl
    0.76
    𝕒
    0.76
    ला
    0.76
    廾
    0.75
    POSITIVE LOGITS
    carried
    0.74
    GPIO
    0.67
    ീയ
    0.67
    unched
    0.67
    image
    0.66
    yuan
    0.65
     carried
    0.64
    implementation
    0.64
     scris
    0.64
     संश्लेषण
    0.64
    Act Density 0.001%

    No Known Activations