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

    Neuronpedia

    INDEX
    Explanations

    describing characteristics or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    മ
    0.44
    WHIT
    0.42
     hammering
    0.41
    ಹ
    0.41
    Selling
    0.39
    О
    0.39
    太平
    0.39
    ना
    0.39
    潭
    0.39
     violence
    0.39
    POSITIVE LOGITS
     resulta
    0.51
    u
    0.50
     carbono
    0.49
     ilus
    0.48
     cabe
    0.48
    !<
    0.47
     tabela
    0.47
     dėl
    0.46
     среднего
    0.46
     calculateur
    0.46
    Act Density 0.000%

    No Known Activations