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

    Neuronpedia

    INDEX
    Explanations

    content ratings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Everest
    -0.09
     doce
    -0.09
     бірінші
    -0.08
    Lincoln
    -0.08
     ilkin
    -0.08
    /json
    -0.08
    $result
    -0.08
    Fal
    -0.08
     luisteren
    -0.08
    อฟ
    -0.08
    POSITIVE LOGITS
     violence
    0.11
     sexuality
    0.10
     immoral
    0.09
     profanity
    0.09
     obscene
    0.09
     erot
    0.09
     Violence
    0.09
     explicit
    0.09
     erotic
    0.09
     violent
    0.09
    Act Density 0.058%

    No Known Activations