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

    Neuronpedia

    INDEX
    Explanations

    ational

    np_max-act · gemini-2.0-flash

    The neuron activates on terms referring to variational methods or principles (e.g. “variational,” “functional,” “Lagrange,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cocoa
    -0.06
     municipal
    -0.06
     Ku
    -0.06
    副
    -0.06
    ộp
    -0.06
    _raise
    -0.06
     Victor
    -0.06
     Hugo
    -0.06
    _async
    -0.06
    ине
    -0.06
    POSITIVE LOGITS
    ерш
    0.08
     исслед
    0.07
     goodwill
    0.07
    issional
    0.06
    .NUM
    0.06
     الوص
    0.06
     Qualcomm
    0.06
    _QUAL
    0.06
    กรรม
    0.06
    ступ
    0.06
    Act Density 0.004%

    No Known Activations