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

    Neuronpedia

    INDEX
    Explanations

    -related

    np_max-act · gemini-2.0-flash

    This neuron does not reliably activate on any tokens and thus does not detect a specific pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    魔
    -0.07
    -cert
    -0.07
    -ins
    -0.07
     مادر
    -0.06
    loe
    -0.06
     Initialize
    -0.06
    Obj
    -0.06
    .getFile
    -0.06
     fclose
    -0.06
     Intern
    -0.06
    POSITIVE LOGITS
    どう
    0.07
    自分
    0.07
    "),"
    0.07
    -depth
    0.06
    "]).
    0.06
     فرمود
    0.06
     safeguards
    0.06
    šku
    0.06
     ayant
    0.06
     Pelosi
    0.06
    Act Density 0.516%

    No Known Activations