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

    Neuronpedia

    INDEX
    Explanations

    RSVP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    b
    0.57
    k
    0.52
     Insurance
    0.52
    c
    0.52
     Duty
    0.48
    ceme
    0.45
    v
    0.44
    od
    0.44
    t
    0.44
     Clubs
    0.44
    POSITIVE LOGITS
    な
    0.54
     недалеко
    0.51
    コスト
    0.51
     США
    0.50
    ྡ
    0.49
    лло
    0.49
     emociones
    0.49
    deployRoot
    0.48
     برطانیہ
    0.48
    ಕ್ತ
    0.47
    Act Density 0.000%

    No Known Activations