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

    Neuronpedia

    INDEX
    Explanations

    creation and construction

    np_max-act · gemini-2.0-flash

    The neuron responds to words that express potential, ability, or likelihood (e.g. “possible,” “make,” “have,” “create,” “better”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .ly
    -0.07
    .dumps
    -0.07
     ří
    -0.06
    .to
    -0.06
    expr
    -0.06
     noted
    -0.06
     EventEmitter
    -0.06
    .org
    -0.06
    itizer
    -0.06
     Talk
    -0.06
    POSITIVE LOGITS
    uba
    0.07
     καν
    0.07
     hormonal
    0.06
    本
    0.06
    _social
    0.06
     दर
    0.06
    administr
    0.06
     hormones
    0.06
    +r
    0.06
    мо
    0.06
    Act Density 0.045%

    No Known Activations