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

    Neuronpedia

    INDEX
    Explanations

    cross

    np_max-act · gemini-2.0-flash

    This neuron detects the term “cross” as used in “cross-section.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _WARNINGS
    -0.07
    _led
    -0.07
    OfWork
    -0.06
     Bard
    -0.06
    exion
    -0.06
    Material
    -0.06
    キュ
    -0.06
     humanoid
    -0.06
     baseUrl
    -0.06
    Dé
    -0.06
    POSITIVE LOGITS
     '
    0.07
    ................................
    0.07
    .Weight
    0.07
     потреб
    0.07
    ประสบ
    0.07
     SS
    0.07
    ('*
    0.07
    _attribute
    0.06
     look
    0.06
     expressing
    0.06
    Act Density 0.001%

    No Known Activations