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

    Neuronpedia

    INDEX
    Explanations

    code files and programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tilt
    0.89
     tilting
    0.87
     tilts
    0.81
    alt
    0.78
    imo
    0.75
    rel
    0.75
    Adr
    0.75
    dL
    0.74
    /-
    0.74
    位数
    0.74
    POSITIVE LOGITS
     File
    0.71
     машин
    0.68
     Verwendung
    0.65
    File
    0.62
     Python
    0.61
     Since
    0.61
    Filename
    0.61
    sempel
    0.60
    T
    0.60
    C
    0.60
    Act Density 0.046%

    No Known Activations