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

    Neuronpedia

    INDEX
    Explanations

    internet text

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is spot first-person or subjective commentary (e.g. “I”, “probably”, “shouldn’t”, quoted opinions, etc.), flagging personal/opinionated statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     enclosed
    -0.07
     dagen
    -0.07
    ψης
    -0.06
    uyo
    -0.06
    blr
    -0.06
    atoes
    -0.06
    IZATION
    -0.06
     WRONG
    -0.06
     stru
    -0.06
     MAC
    -0.06
    POSITIVE LOGITS
     commit
    0.07
     informs
    0.07
     initializer
    0.07
    <IActionResult
    0.07
    .sid
    0.07
     trans
    0.07
     compuls
    0.06
     đáng
    0.06
    _console
    0.06
     subt
    0.06
    Act Density 0.025%

    No Known Activations