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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ال
    -0.07
    stad
    -0.06
    งข
    -0.06
    �
    -0.06
     香港
    -0.06
    .vote
    -0.06
     PackageManager
    -0.06
     tep
    -0.06
    طة
    -0.06
    .Handle
    -0.06
    POSITIVE LOGITS
     identifiable
    0.07
     bo
    0.06
     tuy
    0.06
     baff
    0.06
     disreg
    0.06
    VIRTUAL
    0.06
     zo
    0.06
     Except
    0.06
    参考
    0.06
     Serie
    0.05
    Act Density 0.024%

    No Known Activations