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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens or number-like values (e.g., digits, decimals, measurement figures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .setCode
    -0.06
    .checkSelfPermission
    -0.06
    _raise
    -0.06
     balls
    -0.06
     dir
    -0.06
    456
    -0.06
     yacc
    -0.06
    pNet
    -0.06
    NavBar
    -0.06
    lacak
    -0.06
    POSITIVE LOGITS
    ーカー
    0.07
     Andrew
    0.07
     पहच
    0.06
     Olomou
    0.06
    WORK
    0.06
     Notify
    0.06
    0.06
    MV
    0.06
    (()=>{↵
    0.06
     SwiftUI
    0.06
    Act Density 0.115%

    No Known Activations