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

    Neuronpedia

    INDEX
    Explanations

    future challenges and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Noting
    0.42
     ஏற்கனவே
    0.40
    mselves
    0.40
     noting
    0.40
     crawling
    0.40
    诿
    0.39
    liz
    0.39
     __(
    0.38
    พัน
    0.38
    怎樣
    0.38
    POSITIVE LOGITS
    pro
    0.41
    pr
    0.39
     zvyš
    0.38
    fig
    0.38
     spettac
    0.37
     Pound
    0.37
    projection
    0.36
    GameOver
    0.36
     femenina
    0.36
    포
    0.36
    Act Density 0.000%

    No Known Activations