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

    Neuronpedia

    INDEX
    Explanations

    animal behavior

    np_max-act · gemini-2.0-flash

    The neuron detects words that describe internal attitudes or emotional states (e.g. “interested,” “fearful”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    pNet
    -0.07
    および
    -0.06
     첫
    -0.06
     Kapoor
    -0.06
    楚
    -0.06
     Beer
    -0.06
    -bedroom
    -0.06
     CHANNEL
    -0.06
    Developer
    -0.06
    dbcTemplate
    -0.06
    POSITIVE LOGITS
     sapi
    0.07
    -enh
    0.07
     nez
    0.06
    >>;↵
    0.06
    隐藏
    0.06
    >>,↵
    0.06
     imag
    0.06
     Doing
    0.06
     destroyed
    0.06
     lors
    0.06
    Act Density 0.045%

    No Known Activations