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

    Neuronpedia

    INDEX
    Explanations

    syntax tree generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prévention
    0.54
     prevenir
    0.53
     neuropathy
    0.49
     assuré
    0.48
     déf
    0.48
     wiederum
    0.47
    在他
    0.46
     بالفعل
    0.46
     glut
    0.46
     Schubert
    0.45
    POSITIVE LOGITS
    s
    0.56
    getZoom
    0.52
    on
    0.50
    il
    0.49
    claiming
    0.49
    aerial
    0.48
    text
    0.48
    recommended
    0.48
    sampling
    0.47
    abol
    0.46
    Act Density 0.000%

    No Known Activations