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

    Neuronpedia

    INDEX
    Explanations

    cars and prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ઝડ
    0.42
    抧
    0.41
    混合
    0.39
     ফট
    0.38
     drains
    0.37
    釘
    0.37
     resist
    0.36
     sacr
    0.36
    柱
    0.36
     openly
    0.35
    POSITIVE LOGITS
     rétro
    0.47
     motocicleta
    0.42
    таны
    0.41
     retro
    0.40
    Expr
    0.39
    Outcome
    0.39
    Expiry
    0.38
     democracia
    0.38
     Retro
    0.38
     mecánico
    0.38
    Act Density 0.003%

    No Known Activations