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

    Neuronpedia

    INDEX
    Explanations

    welcome or referral bonuses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erves
    0.64
    ிறது
    0.59
    يج
    0.56
     l
    0.55
    л
    0.55
     quả
    0.54
    िटी
    0.53
     nine
    0.52
     aches
    0.52
    ଲ
    0.52
    POSITIVE LOGITS
    U
    0.64
    Programs
    0.60
    ui
    0.57
    Response
    0.56
    Language
    0.54
    Session
    0.54
    toml
    0.54
    File
    0.54
    Property
    0.54
    Path
    0.53
    Act Density 0.003%

    No Known Activations