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

    Neuronpedia

    INDEX
    Explanations

    associate

    np_max-act · gemini-2.0-flash

    The neuron activates on content words bearing Latinate suffixes (e.g. nouns/​adjectives ending in “-ion,” “-able,” “-ive,” “-ent,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cy
    -0.07
     flipped
    -0.06
    10
    -0.06
    够
    -0.06
    SEX
    -0.06
    荐
    -0.06
    �
    -0.06
    her
    -0.06
    ่อไป
    -0.06
    鲜
    -0.06
    POSITIVE LOGITS
    inges
    0.06
    dsp
    0.06
    entreprise
    0.06
    -rec
    0.06
     acomp
    0.06
     moduleId
    0.06
    (sprite
    0.06
    _comp
    0.06
    ochrome
    0.06
     �
    0.06
    Act Density 0.223%

    No Known Activations