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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    This neuron responds to predicate adjectives and adverbs that evaluate or qualify a state—words expressing desirability, availability, possibility, necessity or informativeness.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    暮
    -0.06
     يا
    -0.06
     Comcast
    -0.06
    uae
    -0.06
    .addTab
    -0.06
    BundleOrNil
    -0.06
    敬
    -0.06
     Spoon
    -0.06
    /games
    -0.06
    lops
    -0.06
    POSITIVE LOGITS
    .nn
    0.07
    ]int
    0.07
    .ceil
    0.06
    าง
    0.06
     prohibition
    0.06
    ilestone
    0.06
     Areas
    0.06
    itung
    0.06
    224
    0.06
     ".";↵
    0.06
    Act Density 0.044%

    No Known Activations