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

    Neuronpedia

    INDEX
    Explanations

    float networking file system libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fixed
    0.43
     fixed
    0.40
    fixed
    0.39
    Nev
    0.39
    Navy
    0.37
    Plasma
    0.37
     FIXED
    0.36
    Refrigerator
    0.36
    Fixed
    0.35
     Ministerio
    0.35
    POSITIVE LOGITS
    row
    0.73
     row
    0.68
     Fl
    0.68
    Fl
    0.65
     Row
    0.65
    Row
    0.63
    fl
    0.63
     ROW
    0.59
     rows
    0.55
    ROW
    0.54
    Act Density 0.000%

    No Known Activations