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

    Neuronpedia

    INDEX
    Explanations

    changes

    np_max-act · gemini-2.0-flash

    This neuron is primarily triggered by the word “changes.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    fort
    -0.08
     Petroleum
    -0.08
     ppl
    -0.07
     prefab
    -0.07
     Elliot
    -0.07
     Elliott
    -0.07
    (ViewGroup
    -0.06
     Txt
    -0.06
     Roosevelt
    -0.06
     Eagles
    -0.06
    POSITIVE LOGITS
    Changes
    0.09
     changes
    0.09
     Changes
    0.08
     change
    0.08
    as
    0.07
    стро
    0.07
    imize
    0.07
    -care
    0.07
    MS
    0.07
    行为
    0.07
    Act Density 0.028%

    No Known Activations