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

    Neuronpedia

    INDEX
    Explanations

    Jokes/quotes

    np_max-act · gemini-2.0-flash

    This neuron activates on the “atoms” joke—specifically the phrase about not trusting atoms because they “make up everything.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    394
    -0.07
    nda
    -0.07
    Lua
    -0.06
    _jwt
    -0.06
    _OBS
    -0.06
    tmp
    -0.06
     дорог
    -0.06
    646
    -0.06
     Kardash
    -0.06
    _since
    -0.06
    POSITIVE LOGITS
    glomer
    0.06
     Parm
    0.06
    erseniz
    0.06
    э
    0.06
    ALER
    0.06
     handwritten
    0.06
    PushButton
    0.06
     编辑
    0.06
    dük
    0.06
     韓
    0.06
    Act Density 0.008%

    No Known Activations