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

    Neuronpedia

    INDEX
    Explanations

    ,v

    np_max-act · gemini-2.0-flash

    This neuron responds to single-letter identifiers (e.g. loop or temporary variables like “i”, “v”, “x”, “y”, “j”) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uator
    -0.07
    út
    -0.07
    suit
    -0.06
     u
    -0.06
    .js
    -0.06
    ̃
    -0.06
    )|
    -0.06
    вали
    -0.06
    NIL
    -0.06
     три
    -0.06
    POSITIVE LOGITS
    riculum
    0.06
    输入
    0.06
     Yunan
    0.06
     Tween
    0.06
    .conn
    0.06
     nez
    0.06
    对于
    0.06
    '+↵
    0.06
     pursuing
    0.06
     Bien
    0.05
    Act Density 0.016%

    No Known Activations