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

    Neuronpedia

    INDEX
    Explanations

    positive outcomes

    np_max-act · gemini-2.0-flash

    This neuron detects promotional or sales-pitch language highlighting product or service benefits.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Widow
    -0.06
     Tob
    -0.06
     tối
    -0.06
     сух
    -0.06
     analyzed
    -0.06
    tog
    -0.06
    Extractor
    -0.06
     Dur
    -0.06
     dân
    -0.06
    Connecting
    -0.06
    POSITIVE LOGITS
    (){
↵
↵
    0.07
    ;",↵
    0.07
    _ALPHA
    0.06
    эф
    0.06
    );

↵
    0.06
    (dat
    0.06
    343
    0.06
     altın
    0.06
     dictated
    0.06
     prostit
    0.06
    Act Density 0.044%

    No Known Activations