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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on subjective-judgment phrases that frame something as “makes no sense to…” or “more important to…,” i.e. comparative or opinionated constructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Workplace
    -0.07
     KG
    -0.07
     bedside
    -0.07
     climbs
    -0.07
    amburg
    -0.07
    owitz
    -0.06
    106
    -0.06
     Dmit
    -0.06
    оже
    -0.06
     rays
    -0.06
    POSITIVE LOGITS
    �
    0.06
     settlers
    0.06
     etk
    0.06
    ड़
    0.06
     presenting
    0.06
    SUR
    0.06
     Establish
    0.06
     flere
    0.06
    enumerate
    0.06
     activations
    0.06
    Act Density 0.036%

    No Known Activations