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

    Neuronpedia

    INDEX
    Explanations

    1mq

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     préférence
    0.91
     poursuivre
    0.86
    િંગ
    0.81
     joue
    0.80
     profondeur
    0.80
    ເພື່ອ
    0.80
     marqué
    0.79
     mangiare
    0.77
     jouer
    0.74
     halen
    0.74
    POSITIVE LOGITS
    ó
    0.91
    m
    0.90
    ljiv
    0.87
    меры
    0.85
    zept
    0.82
    นอน
    0.82
    льника
    0.80
    mén
    0.80
    0
    0.80
    inflammatory
    0.78
    Act Density 0.000%

    No Known Activations