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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash

    The neuron fires on first-person self-introductory statements (e.g. “My name…,” “Currently I’m…,” “I have done…,” “This is…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    parison
    -0.07
     autonomy
    -0.07
     Restrictions
    -0.06
     Там
    -0.06
    planes
    -0.06
    هور
    -0.06
     lw
    -0.06
     default
    -0.06
    Bold
    -0.06
    loc
    -0.06
    POSITIVE LOGITS
    	expected
    0.07
     sociales
    0.06
    กำ
    0.06
     сон
    0.06
    %X
    0.06
    _fmt
    0.06
     výro
    0.06
    	redirect
    0.06
     showToast
    0.06
    gne
    0.06
    Act Density 0.182%

    No Known Activations