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

    Neuronpedia

    INDEX
    Explanations

    say "yst" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     okay
    -0.08
     RAF
    -0.07
     spectrum
    -0.07
    Example
    -0.06
    Shadow
    -0.06
    ([],
    -0.06
    ([↵
    -0.06
    (argv
    -0.06
    Dto
    -0.06
    assignment
    -0.06
    POSITIVE LOGITS
    سي
    0.07
    cess
    0.07
    βολ
    0.07
    itt
    0.06
    ENÍ
    0.06
    hil
    0.06
    كار
    0.06
     удал
    0.06
    zim
    0.06
     CAS
    0.06
    Act Density 0.003%

    No Known Activations