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

    Neuronpedia

    INDEX
    Explanations

    Java code construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IntVar
    0.42
     elevada
    0.40
     elevates
    0.40
    strtotime
    0.39
    㖵
    0.39
     clínicos
    0.38
    𝑝
    0.38
     strtoupper
    0.38
    тана
    0.38
    AGN
    0.38
    POSITIVE LOGITS
     null
    0.93
    null
    0.93
     ((
    0.82
     new
    0.80
    new
    0.78
    ((
    0.66
     Arrays
    0.64
    Arrays
    0.63
     Utils
    0.57
     Util
    0.54
    Act Density 0.007%

    No Known Activations