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

    Neuronpedia

    INDEX
    Explanations

    say "{"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Reality
    0.68
    fak
    0.68
    Review
    0.68
     Review
    0.67
    Ras
    0.65
     दिल्‍ली
    0.64
     stair
    0.63
     Gass
    0.63
     میک
    0.63
     रजिस्टर
    0.62
    POSITIVE LOGITS
    supabase
    0.68
     góc
    0.65
     regreso
    0.64
    ogonad
    0.63
     bacteri
    0.63
    chanics
    0.63
     Saginaw
    0.62
    omeg
    0.62
    emo
    0.62
     база
    0.62
    Act Density 0.005%

    No Known Activations