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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     casc
    -0.06
     Ajax
    -0.06
     tense
    -0.06
    类
    -0.06
     sovereign
    -0.06
    135
    -0.06
     번
    -0.06
     fragile
    -0.06
    DESC
    -0.06
     Swift
    -0.06
    POSITIVE LOGITS
    ansas
    0.08
    )"↵↵
    0.07
     صنع
    0.07
    .EXIT
    0.07
    dbl
    0.07
     tapes
    0.07
    .untracked
    0.06
     sued
    0.06
     Firearms
    0.06
    _;↵
    0.06
    Act Density 0.002%

    No Known Activations