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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Communication
    -0.07
     Atomic
    -0.07
    icerca
    -0.06
    ="../
    -0.06
     Roo
    -0.06
    Enumerator
    -0.06
    oulos
    -0.06
     Fakültesi
    -0.06
     değildir
    -0.06
     ilma
    -0.06
    POSITIVE LOGITS
     capit
    0.07
    áf
    0.06
    PMC
    0.06
    ペ
    0.06
    .Timer
    0.06
    NSBundle
    0.06
    เม
    0.06
    彦
    0.06
     Moral
    0.06
    WithType
    0.06
    Act Density 0.017%

    No Known Activations