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

    Neuronpedia

    INDEX
    Explanations

    differences between two things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     červ
    -0.07
    Ended
    -0.07
     Arap
    -0.06
    .Attributes
    -0.06
     DIAG
    -0.06
     disco
    -0.06
     Criminal
    -0.06
    Exited
    -0.06
     cuối
    -0.06
    培训
    -0.06
    POSITIVE LOGITS
     humour
    0.07
    :E
    0.06
    ﻮ
    0.06
    alance
    0.06
    -hide
    0.06
    Modifier
    0.06
    مد
    0.06
    Dlg
    0.06
    (game
    0.06
    asy
    0.06
    Act Density 0.061%

    No Known Activations