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

    Neuronpedia

    INDEX
    Explanations

    square roots `√`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     workload
    0.46
     note
    0.44
     crossbow
    0.43
     edition
    0.40
     miércoles
    0.40
    加工
    0.39
    elipe
    0.39
     oligonucleotide
    0.39
     contraction
    0.39
     bowel
    0.39
    POSITIVE LOGITS
     กรณี
    0.47
     במ
    0.44
     צי
    0.44
     وتح
    0.42
    ❉
    0.42
    Heights
    0.40
     كلكم
    0.39
     nachos
    0.39
     glPopMatrix
    0.38
     건물
    0.38
    Act Density 0.001%

    No Known Activations