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

    Neuronpedia

    INDEX
    Explanations

    city and state names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multiplicative
    0.47
     YAML
    0.46
     regex
    0.45
     Maths
    0.45
     recombin
    0.45
     Tencent
    0.45
     quantifier
    0.44
     Xu
    0.44
     Antwort
    0.43
     Recursive
    0.43
    POSITIVE LOGITS
     Jacksonville
    1.14
     Kansas
    1.11
     Seattle
    1.10
     Atlanta
    1.10
     Minneapolis
    1.09
     Houston
    1.09
     Denver
    1.09
     Pittsburgh
    1.08
     Dallas
    1.07
     Baltimore
    1.06
    Act Density 0.025%

    No Known Activations