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

    Neuronpedia

    INDEX
    Explanations

    110

    np_max-act · gemini-2.0-flash

    This neuron detects numeric substrings from DOI identifiers (e.g. the “1103” in “10.1103/…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _v
    -0.07
     đề
    -0.07
    dia
    -0.07
    rios
    -0.07
    μέ
    -0.07
    'eau
    -0.06
    _x
    -0.06
    /utility
    -0.06
     bottoms
    -0.06
    frames
    -0.06
    POSITIVE LOGITS
     İnsan
    0.07
    Apellido
    0.07
     سخن
    0.06
     attending
    0.06
     सरक
    0.06
     grotes
    0.06
     엄
    0.06
     百
    0.06
     속
    0.06
     thankfully
    0.06
    Act Density 0.000%

    No Known Activations