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

    Neuronpedia

    INDEX
    Explanations

    character

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਲੋ
    0.65
     লোক
    0.64
     خلي
    0.64
    সংযোগ
    0.64
     Theo
    0.62
     analogue
    0.60
     mie
    0.60
    랭
    0.59
    pumpkin
    0.58
     aussch
    0.58
    POSITIVE LOGITS
    ter
    1.30
    ater
    1.21
    ters
    1.19
    Ter
    1.17
     ter
    1.17
    ers
    1.15
    TER
    1.13
    TERS
    1.12
     Ter
    1.09
    ERS
    1.08
    Act Density 0.068%

    No Known Activations