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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron responds to standard open-source license boilerplate, especially the warranty/disclaimer and distribution clauses frequently found in GNU-style headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    láš
    -0.07
     Gro
    -0.07
     Том
    -0.07
    _LESS
    -0.07
    фік
    -0.07
    ụp
    -0.07
     реп
    -0.07
    shapes
    -0.06
     Philosophy
    -0.06
     BET
    -0.06
    POSITIVE LOGITS
    azu
    0.06
    ằ
    0.06
    owment
    0.06
     направ
    0.06
    Ac
    0.06
     الدولي
    0.06
     efficiently
    0.06
    携
    0.06
    IMER
    0.06
     ngăn
    0.06
    Act Density 0.001%

    No Known Activations