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

    Neuronpedia

    INDEX
    Explanations

    descriptions and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وصلة
    -0.47
    -
    -0.41
     к
    -0.41
     calls
    -0.41
    i
    -0.40
     which
    -0.39
     yang
    -0.38
    Then
    -0.38
     di
    -0.36
     который
    -0.36
    POSITIVE LOGITS
     שוליים
    0.86
    adays
    0.79
    etheless
    0.79
    ChildScrollView
    0.77
    NUMX
    0.75
    neté
    0.73
    IVEREF
    0.71
    theless
    0.71
     insuffisamment
    0.71
     ويكيميديا
    0.70
    Act Density 0.036%

    No Known Activations