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

    Neuronpedia

    INDEX
    Explanations

    Fortify Program URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SAFER
    0.42
     ас
    0.39
     প্রের
    0.39
    ас
    0.39
     Psp
    0.39
     глоба
    0.38
     ज
    0.38
    कूल
    0.38
     realice
    0.37
    jupyter
    0.37
    POSITIVE LOGITS
     FT
    0.48
     Darren
    0.43
    FT
    0.42
    Ft
    0.41
    فت
    0.40
     Lauderdale
    0.40
     Fort
    0.40
    fortun
    0.40
     Ft
    0.39
    cart
    0.39
    Act Density 0.019%

    No Known Activations