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

    Neuronpedia

    INDEX
    Explanations

    sudden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hero
    0.45
     playoffs
    0.39
    弱
    0.39
    ksom
    0.39
     widz
    0.38
     vet
    0.38
     Trevor
    0.38
    som
    0.37
     героя
    0.37
    }),
    0.37
    POSITIVE LOGITS
    Sud
    0.48
     স্থানে
    0.41
    Sullivan
    0.40
    Gruppe
    0.40
     sudden
    0.40
    Mare
    0.40
    Prints
    0.40
     Sudden
    0.39
    Suddenly
    0.39
    Dere
    0.39
    Act Density 0.000%

    No Known Activations