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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash

    This neuron activates on hyphens, i.e. it detects parts of hyphenated words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     thức
    -0.06
     ح
    -0.06
    619
    -0.06
    학회
    -0.06
    иш
    -0.06
    _label
    -0.06
     حديث
    -0.06
    Addresses
    -0.06
    .feedback
    -0.06
     unnoticed
    -0.06
    POSITIVE LOGITS
     　
    0.07
    lk
    0.07
    ー�
    0.07
     callbacks
    0.06
     deleteUser
    0.06
     @$
    0.06
    ่อ
    0.06
     ô
    0.06
    SOR
    0.06
    основ
    0.06
    Act Density 0.070%

    No Known Activations