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

    Neuronpedia

    INDEX
    Explanations

    rewards

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “prize” or “prizes” (and related discussion of prize‐based rewards or competitions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     XS
    -0.07
    ("")↵
    -0.07
     PLL
    -0.06
     todos
    -0.06
     hart
    -0.06
     Haram
    -0.06
     Beats
    -0.06
     приз
    -0.06
     контра
    -0.06
    하세요
    -0.06
    POSITIVE LOGITS
    .Nav
    0.07
    size
    0.07
    scp
    0.06
    mime
    0.06
     replic
    0.06
     satur
    0.06
     cartesian
    0.06
     Wit
    0.06
    ublic
    0.06
     rồi
    0.06
    Act Density 0.038%

    No Known Activations