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

    Neuronpedia

    INDEX
    Explanations

    aliexpress, poco, ender, anycubic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ط
    0.62
    我
    0.59
    ર
    0.58
    तू
    0.56
     pusieron
    0.56
    ினர்
    0.55
    ICPSR
    0.55
     endangering
    0.54
    D
    0.54
    मी
    0.54
    POSITIVE LOGITS
    sen
    0.60
     powy
    0.56
     ongeveer
    0.54
     päiv
    0.54
     بیش
    0.53
     vall
    0.53
     ١
    0.53
     aliexpress
    0.53
     nahe
    0.52
     zat
    0.51
    Act Density 0.001%

    No Known Activations