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

    Neuronpedia

    INDEX
    Explanations

    java package imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stafford
    0.30
     Salamanca
    0.30
     Somerville
    0.29
    臼
    0.29
     startGame
    0.28
     Farmington
    0.28
     spectrom
    0.27
     shank
    0.27
     있지만
    0.27
     Mohr
    0.27
    POSITIVE LOGITS
    youtube
    0.34
     hate
    0.30
    us
    0.29
     hatred
    0.29
    ē
    0.29
    ß
    0.28
    ពិ
    0.28
     comprador
    0.28
    හු
    0.28
     ä
    0.28
    Act Density 0.001%

    No Known Activations