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

    Neuronpedia

    INDEX
    Explanations

    Nineteen Eighty-Four

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lots
    -0.07
     types
    -0.07
     plenty
    -0.07
    igned
    -0.07
    有个
    -0.07
     ciudad
    -0.07
     misunderstand
    -0.07
    ideshow
    -0.06
     bite
    -0.06
     decltype
    -0.06
    POSITIVE LOGITS
     sublic
    0.07
    _strlen
    0.07
    눔
    0.07
    ﱐ
    0.07
     Mods
    0.07
    -sample
    0.07
    perf
    0.07
    .Car
    0.07
    .lifecycle
    0.07
     Lion
    0.06
    Act Density 0.007%

    No Known Activations