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

    Neuronpedia

    INDEX
    Explanations

    capability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ドラマ
    -0.07
    .IsNullOrEmpty
    -0.07
    氨
    -0.06
    ierung
    -0.06
     Electron
    -0.06
     Text
    -0.06
     defeating
    -0.06
    間に
    -0.06
     unarmed
    -0.06
    戋
    -0.06
    POSITIVE LOGITS
    .lang
    0.08
    不错
    0.07
    .Framework
    0.07
    /tos
    0.07
    과장
    0.07
     blink
    0.07
     rooftop
    0.07
     literals
    0.06
    .beans
    0.06
    kea
    0.06
    Act Density 0.219%

    No Known Activations