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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash

    This neuron detects when the text asks to “execute the instruction of” (i.e. requests to carry out or combine given instructions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     deflect
    -0.07
    .ut
    -0.07
    _chr
    -0.06
    TouchableOpacity
    -0.06
    tec
    -0.06
     merges
    -0.06
    ynthesis
    -0.06
    .InvariantCulture
    -0.06
    овал
    -0.06
    =set
    -0.06
    POSITIVE LOGITS
    ;"></
    0.07
    %↵↵
    0.07
    ğine
    0.07
     Animation
    0.07
    :"+
    0.06
     kindly
    0.06
    -or
    0.06
    eného
    0.06
    TEM
    0.06
    이트
    0.06
    Act Density 0.001%

    No Known Activations