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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on in‐code identifiers—especially camelCase names—rather than on comments or punctuation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    алю
    -0.06
     psychotic
    -0.06
     Rapids
    -0.06
    alphabet
    -0.06
    'яз
    -0.06
     разом
    -0.06
    яз
    -0.06
    　　　 　 　 　
    -0.06
     잡담
    -0.06
    pants
    -0.06
    POSITIVE LOGITS
     Science
    0.07
    ुण
    0.07
     uygun
    0.06
     طريق
    0.06
    (vertical
    0.06
     django
    0.06
     Showcase
    0.06
     fruitful
    0.06
     爱
    0.06
    .tc
    0.06
    Act Density 0.090%

    No Known Activations