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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DrvGPIO
    0.64
     textural
    0.63
     hurtful
    0.62
    ሟ
    0.62
     innocuous
    0.61
     다양한
    0.61
    多种
    0.61
     ridicule
    0.60
     skillful
    0.60
     impure
    0.60
    POSITIVE LOGITS
    .
    0.84
     selatan
    0.78
    land
    0.72
    ®.
    0.65
     Üniversitesi
    0.65
     (“
    0.64
    ville
    0.64
     Selatan
    0.63
     Utara
    0.63
     outskirts
    0.62
    Act Density 0.681%

    No Known Activations