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

    Neuronpedia

    INDEX
    Explanations

    mathematical inequalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ы
    0.74
    ъ
    0.74
    ö
    0.69
    1
    0.67
    ás
    0.65
    容易
    0.63
    ের
    0.61
     tendencia
    0.61
     ugy
    0.61
    ę
    0.61
    POSITIVE LOGITS
    רי
    0.76
    i
    0.73
    י
    0.73
     encapsulates
    0.72
    נים
    0.71
     irradiance
    0.70
    με
    0.69
    jus
    0.69
    to
    0.68
     നേടി
    0.66
    Act Density 0.001%

    No Known Activations