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

    Neuronpedia

    INDEX
    Explanations

    requests, instructions

    np_max-act · gemini-2.0-flash

    This neuron activates on the phrase “Stay in character!”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    mekte
    -0.07
    getSimpleName
    -0.07
     Fork
    -0.07
     simpler
    -0.06
    pricing
    -0.06
     dici
    -0.06
     princ
    -0.06
    步
    -0.06
     Yao
    -0.06
    avigator
    -0.06
    POSITIVE LOGITS
    arbon
    0.07
    532
    0.07
    ('.',
    0.06
     packageName
    0.06
    )<
    0.06
    /${
    0.06
     ROLE
    0.06
    *\
    0.06
    _series
    0.06
    ConfigurationException
    0.06
    Act Density 0.003%

    No Known Activations