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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aware
    -0.07
    bud
    -0.07
    AccessType
    -0.07
     bamb
    -0.07
     �
    -0.07
     האינטרנט
    -0.07
     tast
    -0.06
    .JPanel
    -0.06
     stamps
    -0.06
    أم
    -0.06
    POSITIVE LOGITS
     lessons
    0.07
     tiếng
    0.07
    (Source
    0.06
     עמוק
    0.06
    充分发挥
    0.06
    (levels
    0.06
    Salary
    0.06
    Ⓖ
    0.06
    得出
    0.06
     سنة
    0.06
    Act Density 0.027%

    No Known Activations