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

    Neuronpedia

    INDEX
    Explanations

    fixed

    np_max-act · gemini-2.0-flash

    This neuron detects CSS positioning keywords, especially “sticky” (and related positioning terms like “fixed”) in style definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Holt
    -0.06
     pře
    -0.06
    PackageName
    -0.06
     melhores
    -0.06
    erten
    -0.06
    Trail
    -0.06
     مان
    -0.06
    callbacks
    -0.06
     κάθε
    -0.06
     usuario
    -0.06
    POSITIVE LOGITS
    agree
    0.07
     livro
    0.07
    .issue
    0.06
    splice
    0.06
     felt
    0.06
    _INLINE
    0.06
    Exclude
    0.06
    _leave
    0.06
    以下
    0.06
     cling
    0.06
    Act Density 0.001%

    No Known Activations