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

    Neuronpedia

    INDEX
    Explanations

    errors and exceptions

    np_max-act · gemini-2.0-flash

    error messages related to compilation and build failures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rikes
    -0.07
    ------------------------------------------------
    -0.07
    emiz
    -0.06
     popping
    -0.06
    ("--------------------------------
    -0.06
    IDES
    -0.06
     derivatives
    -0.06
     além
    -0.06
     Этот
    -0.06
    ischen
    -0.06
    POSITIVE LOGITS
    沃
    0.06
    vla
    0.06
     Dell
    0.06
     muži
    0.06
    머
    0.06
     Sicher
    0.06
     frei
    0.06
     crush
    0.06
    เศ
    0.06
     throw
    0.06
    Act Density 0.011%

    No Known Activations