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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations/short identifiers

    np_max-act · gemini-2.0-flash

    structured data related to items or components within a system.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -0.08
    22
    -0.08
    paněl
    -0.07
     paz
    -0.07
    23
    -0.07
    杨
    -0.07
    -0.07
     puzzle
    -0.07
    opolitan
    -0.07
    txn
    -0.07
    POSITIVE LOGITS
    f
    0.17
    F
    0.15
    of
    0.14
    af
    0.14
    CF
    0.14
    if
    0.13
    ff
    0.13
    ф
    0.13
    ef
    0.13
    フ
    0.13
    Act Density 0.344%

    No Known Activations