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

    Neuronpedia

    INDEX
    Explanations

    giants

    np_max-act · gemini-2.0-flash

    It activates on occurrences of the proper noun referring to the sports team (mentions of the Giants).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    harma
    -0.07
     interviews
    -0.06
     Ire
    -0.06
     indigenous
    -0.06
     Vish
    -0.06
    ören
    -0.06
     pray
    -0.06
     IDD
    -0.06
    .GetValue
    -0.06
    rowth
    -0.06
    POSITIVE LOGITS
     giants
    0.17
     Giants
    0.16
     Giant
    0.13
     giant
    0.12
     gigantic
    0.08
     Titan
    0.08
     Titans
    0.08
     titan
    0.08
    巨
    0.07
     Dodgers
    0.07
    Act Density 0.005%

    No Known Activations