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

    Neuronpedia

    INDEX
    Explanations

    how it works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xiety
    1.24
     غوره
    1.17
    liquer
    1.16
    pillars
    1.14
     लकार
    1.14
    EMBER
    1.13
     важ
    1.13
    ので
    1.11
    愪
    1.11
    ங்கிணை
    1.11
    POSITIVE LOGITS
    TypeArguments
    1.02
     কে
    0.98
     morgen
    0.95
     pública
    0.92
    yata
    0.89
     realtà
    0.89
     vigor
    0.88
     And
    0.88
     Públic
    0.87
     bebidas
    0.86
    Act Density 0.000%

    No Known Activations