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

    Neuronpedia

    INDEX
    Explanations

    academic journals or URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     explicitly
    0.40
    agliari
    0.39
    obie
    0.39
     حافظ
    0.38
    ynt
    0.38
     appare
    0.38
     Mär
    0.37
    مبر
    0.37
    oble
    0.37
    aling
    0.36
    POSITIVE LOGITS
     MAGAZINE
    0.42
     בני
    0.41
    şti
    0.41
     Magazine
    0.38
    হেল
    0.38
    SHUNT
    0.38
    ца
    0.37
    Magazine
    0.37
    ভির
    0.37
    IUS
    0.37
    Act Density 0.001%

    No Known Activations