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

    Neuronpedia

    INDEX
    Explanations

    every

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lemetry
    -0.07
    目录
    -0.07
     ON
    -0.07
    归属
    -0.07
     Mem
    -0.07
    @app
    -0.07
     competitive
    -0.06
    ALT
    -0.06
    clado
    -0.06
    ADATA
    -0.06
    POSITIVE LOGITS
     š
    0.07
    璠
    0.07
    ɂ
    0.07
    ｦ
    0.07
    ()};↵
    0.06
    comboBox
    0.06
    waukee
    0.06
     schö
    0.06
    icare
    0.06
     Bowling
    0.06
    Act Density 0.027%

    No Known Activations