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

    Neuronpedia

    INDEX
    Explanations

    keep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     غذایی
    -0.06
    dess
    -0.06
    ‚ط
    -0.06
     Welch
    -0.06
    cond
    -0.06
    而
    -0.06
    orama
    -0.06
    �
    -0.06
     Thương
    -0.06
    عة
    -0.06
    POSITIVE LOGITS
     annot
    0.07
     June
    0.07
     stick
    0.07
     organisers
    0.07
     zo
    0.06
    .perm
    0.06
     AV
    0.06
     reflect
    0.06
     flexibility
    0.06
     примі
    0.06
    Act Density 0.001%

    No Known Activations