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

    Neuronpedia

    INDEX
    Explanations

    judgment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Judgment
    -1.14
     Judgement
    -1.07
     judgment
    -1.05
     المعيارى
    -0.97
     JUDGMENT
    -0.96
    judgment
    -0.96
     يتيمه
    -0.95
    Judgment
    -0.95
     judgement
    -0.94
     transfieras
    -0.91
    POSITIVE LOGITS
    s
    0.57
    al
    0.57
    es
    0.53
    en
    0.50
    ly
    0.49
    sal
    0.49
    son
    0.48
    تها
    0.47
    ,
    0.47
     lain
    0.46
    Act Density 0.068%

    No Known Activations