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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron activates on abstract nouns referring to lifestyle qualities or states—especially words like “simplicity,” “freedom,” or “bustle.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    虎
    -0.07
     teil
    -0.06
    _GPS
    -0.06
     createSelector
    -0.06
    =tmp
    -0.06
     futile
    -0.06
    able
    -0.06
    CTRL
    -0.06
    astic
    -0.06
    ABILITY
    -0.06
    POSITIVE LOGITS
     Rahmen
    0.06
    bies
    0.06
     entities
    0.06
    /original
    0.06
    .broadcast
    0.06
     preorder
    0.06
     Vehicles
    0.06
     investigator
    0.06
    ainties
    0.06
     prefer
    0.06
    Act Density 0.054%

    No Known Activations