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

    Neuronpedia

    INDEX
    Explanations

    HTML/CSS code

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect blocks of programming or markup code—i.e. the syntactic structure of code rather than ordinary prose.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Formula
    -0.07
    _bloc
    -0.07
     Liberals
    -0.07
    _si
    -0.06
    tal
    -0.06
    .entry
    -0.06
    因
    -0.06
     عق
    -0.06
    .user
    -0.06
    尺
    -0.06
    POSITIVE LOGITS
    elight
    0.07
     velkou
    0.07
     hWnd
    0.06
     Funk
    0.06
     recreate
    0.06
    ürger
    0.06
     usr
    0.06
    .Gr
    0.06
     �
    0.06
    oloj
    0.06
    Act Density 0.013%

    No Known Activations