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

    Neuronpedia

    INDEX
    Explanations

    Acronyms

    np_max-act · gemini-2.0-flash

    This neuron activates on multi-letter uppercase acronyms or initialisms (e.g., SSA, AST, KPI) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     робот
    -0.07
    جو
    -0.07
    (textBox
    -0.07
    tach
    -0.07
    λικ
    -0.07
    rank
    -0.07
     plumber
    -0.07
    iron
    -0.06
     chính
    -0.06
    事故
    -0.06
    POSITIVE LOGITS
    JT
    0.09
     LN
    0.08
    SL
    0.08
    RG
    0.08
     RM
    0.08
     BG
    0.08
     NH
    0.08
     WP
    0.08
     WL
    0.08
    WB
    0.08
    Act Density 1.241%

    No Known Activations