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

    Neuronpedia

    INDEX
    Explanations

    coercive actions and mother tongue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Burger
    0.43
     dignidad
    0.40
    \.
    0.40
    ົບ
    0.39
     समझा
    0.38
     ክብ
    0.37
    DebugTest
    0.37
    ırl
    0.35
    Invocation
    0.35
    FIED
    0.35
    POSITIVE LOGITS
     His
    0.48
     Hickory
    0.45
     lives
    0.41
     Coats
    0.39
     हरे
    0.38
     coats
    0.38
     voici
    0.38
     seeks
    0.38
     Heron
    0.38
     देखती
    0.37
    Act Density 0.001%

    No Known Activations