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

    Neuronpedia

    INDEX
    Explanations

    corrections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    억
    -0.07
    τών
    -0.06
     waves
    -0.06
    etrics
    -0.06
     Hav
    -0.06
    義
    -0.06
     sea
    -0.06
    ์ล
    -0.06
     vyh
    -0.06
    전
    -0.06
    POSITIVE LOGITS
     arousal
    0.07
     Anita
    0.07
    627
    0.06
    (Collection
    0.06
    Terminate
    0.06
    .parentElement
    0.06
     ihtiyaç
    0.06
     kata
    0.06
    solve
    0.06
    -reviewed
    0.06
    Act Density 0.048%

    No Known Activations