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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron detects discourse‐level transition markers—particularly comparative adverbs like “Likewise” or “Similarly” and the phrasing that follows them.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tuple
    -0.06
    Press
    -0.06
    Option
    -0.06
    _BLACK
    -0.06
     davon
    -0.06
     Mutable
    -0.06
    Coach
    -0.06
    Despite
    -0.06
     Increases
    -0.06
     😉
    -0.06
    POSITIVE LOGITS
    .rdf
    0.07
    .visitVarInsn
    0.07
    .Primary
    0.07
    ,R
    0.06
     району
    0.06
     flexGrow
    0.06
     ked
    0.06
    TYPO
    0.06
     号
    0.06
     abol
    0.06
    Act Density 0.060%

    No Known Activations