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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     esternos
    -0.56
    used
    -0.55
    Used
    -0.53
    ستخدم
    -0.53
    帖最后由
    -0.52
     used
    -0.47
     Used
    -0.47
     verwendet
    -0.47
     används
    -0.46
     brukes
    -0.46
    POSITIVE LOGITS
    IUrlHelper
    0.85
     predicting
    0.78
     classifying
    0.77
     uncovering
    0.75
     summarizing
    0.75
     assembling
    0.74
     simulating
    0.73
     condemning
    0.72
     attaching
    0.72
     depicting
    0.72
    Act Density 0.037%

    No Known Activations