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

    Neuronpedia

    INDEX
    Explanations

    bindi or subscription

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estimado
    0.80
     impacto
    0.79
     berjalan
    0.77
     lengkap
    0.75
    යින්
    0.74
     diminta
    0.73
     tentang
    0.73
    σίας
    0.73
    yed
    0.73
    y
    0.72
    POSITIVE LOGITS
    Blu
    0.78
    ｑ
    0.77
    まぁ
    0.77
    蚪
    0.77
    0.75
    았
    0.75
    то
    0.74
     КО
    0.74
     memberships
    0.72
    িল
    0.72
    Act Density 0.000%

    No Known Activations