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

    Neuronpedia

    INDEX
    Explanations

    gressive

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “aggressive” (and its close morphological variants like “aggression”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    atalog
    -0.07
     analý
    -0.07
     intertwined
    -0.06
     Land
    -0.06
     Sala
    -0.06
     Wyn
    -0.06
     ThreadPool
    -0.06
     theoret
    -0.06
     Tan
    -0.06
    Land
    -0.06
    POSITIVE LOGITS
     aggressive
    0.15
     aggressively
    0.12
     aggression
    0.11
     aggress
    0.10
    지고
    0.08
    meg
    0.08
    بش
    0.07
     angst
    0.07
    џџ
    0.07
    j
    0.07
    Act Density 0.005%

    No Known Activations