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

    Neuronpedia

    INDEX
    Explanations

    ate

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens making up the word “vacate,” i.e. detecting the appellate-disposition term “vacate.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     deeper
    -0.07
     собою
    -0.07
    developers
    -0.07
     more
    -0.06
     раздел
    -0.06
    	swap
    -0.06
    _Base
    -0.06
     Miscellaneous
    -0.06
    .Utils
    -0.06
     собой
    -0.06
    POSITIVE LOGITS
     Baton
    0.07
    CAA
    0.06
     Photo
    0.06
     Kendrick
    0.06
     Vatican
    0.06
     Victorian
    0.06
     Fallout
    0.06
     �
    0.06
     �
    0.06
    coe
    0.06
    Act Density 0.002%

    No Known Activations