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

    Neuronpedia

    INDEX
    Explanations

    synthetic formulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anterie
    0.41
     sparsely
    0.38
    Formatter
    0.38
    Josh
    0.37
     infek
    0.37
    zoomSeekBar
    0.36
    玉米
    0.36
     অভিষ
    0.35
    hus
    0.35
     Parses
    0.35
    POSITIVE LOGITS
     Pratap
    0.40
     NOL
    0.40
    artifactId
    0.39
     NOC
    0.39
    quita
    0.38
    हन
    0.38
    mets
    0.38
     haystack
    0.38
     mew
    0.37
     값이
    0.36
    Act Density 0.000%

    No Known Activations