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

    Neuronpedia

    INDEX
    Explanations

    Elara progressive Theron isn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oligos
    0.40
     Apoll
    0.40
    ourier
    0.40
     soov
    0.40
    (−
    0.40
     recommandé
    0.39
     न्यायिक
    0.39
     tuli
    0.39
    :“
    0.38
     extrap
    0.38
    POSITIVE LOGITS
    zers
    0.38
    ub
    0.37
    独特
    0.37
    най
    0.36
    ipal
    0.35
     રી
    0.34
    上手
    0.33
    ูด
    0.33
    IndexArray
    0.33
    directories
    0.32
    Act Density 0.000%

    No Known Activations