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

    Neuronpedia

    INDEX
    Explanations

    fire support, teams, VM, classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тные
    0.44
     Whirl
    0.43
     Water
    0.42
     Constraints
    0.42
     Dealing
    0.42
     Modern
    0.41
     Fossil
    0.41
     Environmental
    0.40
    Constraints
    0.40
     Electromagnetic
    0.40
    POSITIVE LOGITS
     superiority
    0.43
     intimidation
    0.43
     homosexuality
    0.43
    ケーション
    0.42
    食事
    0.41
    灌
    0.40
     mistrust
    0.40
     bigotry
    0.40
    იმ
    0.39
    {//
    0.39
    Act Density 0.059%

    No Known Activations