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

    Neuronpedia

    INDEX
    Explanations

    animated visuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CONCLUSIONES
    -0.81
    רְ
    -0.80
     \'
    -0.80
    graduate
    -0.77
     &$
    -0.77
    很容易
    -0.77
    abonnement
    -0.77
     konsep
    -0.77
     Zacks
    -0.76
     Würde
    -0.76
    POSITIVE LOGITS
     cinnamon
    0.95
     działa
    0.86
    lingo
    0.85
    iato
    0.85
    ensões
    0.83
    ValueChanged
    0.82
     groots
    0.81
     ویکی‌پدیا
    0.81
    腩
    0.81
     GIF
    0.81
    Act Density 0.008%

    No Known Activations