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

    Neuronpedia

    INDEX
    Explanations

    crucial importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.52
    d
    0.50
    ด
    0.47
    DS
    0.46
    ela
    0.45
    oot
    0.45
    egg
    0.45
    t
    0.45
    ucked
    0.44
    ucks
    0.44
    POSITIVE LOGITS
    年に
    0.60
     położ
    0.52
     tới
    0.51
     determinación
    0.50
     contributions
    0.49
     contribution
    0.48
    megen
    0.48
    ніх
    0.48
     pertama
    0.48
     popolazione
    0.48
    Act Density 0.000%

    No Known Activations