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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     became
    -0.85
     program
    -0.73
     названия
    -0.72
     Crown
    -0.72
     at
    -0.71
     спре
    -0.71
    プログラム
    -0.69
     Vas
    -0.69
     комна
    -0.68
     الصحة
    -0.68
    POSITIVE LOGITS
     hígado
    0.86
    CRAFT
    0.84
    SAM
    0.82
    PASSED
    0.81
     shou
    0.81
     希望
    0.79
    essentially
    0.77
    Itens
    0.75
     HOP
    0.75
    need
    0.75
    Act Density 0.046%

    No Known Activations