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

    Neuronpedia

    INDEX
    Explanations

    character names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    到底是
    -0.07
    是
    -0.07
    ガン
    -0.06
    越多
    -0.06
    뵉
    -0.06
     identifiable
    -0.06
    럇
    -0.06
     jed
    -0.06
    uja
    -0.06
     destination
    -0.06
    POSITIVE LOGITS
     Retrofit
    0.07
    _clone
    0.07
    .impl
    0.07
    -shadow
    0.07
     classroom
    0.07
     shoreline
    0.07
     destroy
    0.06
    '],↵↵
    0.06
    cro
    0.06
     Military
    0.06
    Act Density 0.050%

    No Known Activations