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

    Neuronpedia

    INDEX
    Explanations

    group members or everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thousands
    0.61
    thousands
    0.53
     billions
    0.52
     Thousands
    0.52
    Thousands
    0.51
     trillions
    0.51
     localized
    0.49
     multe
    0.49
     millions
    0.48
     derived
    0.47
    POSITIVE LOGITS
    全員
    1.07
     members
    0.93
     teammates
    0.93
    メンバー
    0.89
    成员
    0.88
     দুইজন
    0.88
    everyone
    0.87
    Everyone
    0.84
    队员
    0.84
     everyone
    0.84
    Act Density 0.045%

    No Known Activations