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

    Neuronpedia

    INDEX
    Explanations

    object

    np_max-act · gemini-2.0-flash

    This neuron detects high-level Scala code declarations and imports (e.g. the keywords `object`, `trait`, `import`, `sealed` at top‐level).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     politician
    -0.07
     ArrayList
    -0.07
     yıldız
    -0.06
     چیز
    -0.06
     announce
    -0.06
     gras
    -0.06
    Calendar
    -0.06
    ,N
    -0.06
    )-
    -0.06
    .lastName
    -0.06
    POSITIVE LOGITS
    کم
    0.07
    esson
    0.06
    adf
    0.06
    PRI
    0.06
    hwnd
    0.06
    .'</
    0.06
    حب
    0.06
    .simpleButton
    0.06
    adresse
    0.06
     @{$
    0.06
    Act Density 0.001%

    No Known Activations