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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron fires on the “in (…)” clause of Windows batch FOR loops, effectively detecting FOR-IN loop syntax.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    太郎
    -0.07
     Till
    -0.07
     obliv
    -0.06
    新增
    -0.06
     getStatus
    -0.06
    "])
↵
    -0.06
    	to
    -0.06
    ';↵
    -0.06
     Perhaps
    -0.06
     Roma
    -0.06
    POSITIVE LOGITS
     податков
    0.07
    .ExecuteScalar
    0.06
     ebooks
    0.06
    -inspired
    0.06
    481
    0.06
    imoto
    0.06
    kinson
    0.06
     insane
    0.06
     diversity
    0.06
    ział
    0.06
    Act Density 0.001%

    No Known Activations