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

    Neuronpedia

    INDEX
    Explanations

    can/cannot use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inductive
    0.44
    gross
    0.41
     Nathan
    0.41
    يف
    0.40
    ANSI
    0.40
    ന്യ
    0.39
    commonly
    0.39
    availability
    0.39
    observations
    0.39
    誘導
    0.38
    POSITIVE LOGITS
    t
    0.48
     enact
    0.44
     nutzt
    0.44
     использовать
    0.43
     inclui
    0.42
    ಡಿಯ
    0.41
     bruge
    0.41
    टिल
    0.41
     accedi
    0.41
     koristiti
    0.40
    Act Density 0.000%

    No Known Activations