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

    Neuronpedia

    INDEX
    Explanations

    intervene, stepped in, takes over

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     culminated
    0.45
     vergessen
    0.39
     menikmati
    0.39
     formative
    0.39
     culmination
    0.39
     burg
    0.38
     دیتا
    0.38
     ܗ
    0.38
     négl
    0.37
     Achieve
    0.37
    POSITIVE LOGITS
     intervene
    1.86
     intervened
    1.80
     interven
    1.77
     intervenir
    1.64
     intervention
    1.63
    介入
    1.61
     stepped
    1.55
     swoop
    1.48
    intervention
    1.48
     intervening
    1.47
    Act Density 0.042%

    No Known Activations