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

    Neuronpedia

    INDEX
    Explanations

    parables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     challenger
    -0.07
    /container
    -0.07
    hores
    -0.07
     sits
    -0.07
    וכל
    -0.07
     Ô
    -0.07
    不变
    -0.06
    �
    -0.06
    迕
    -0.06
    .Void
    -0.06
    POSITIVE LOGITS
    rna
    0.07
    IpAddress
    0.07
     AnyObject
    0.07
    簡単に
    0.07
    عزيز
    0.07
     Adventure
    0.06
    cassert
    0.06
    TÜRK
    0.06
    片区
    0.06
     يعرف
    0.06
    Act Density 0.004%

    No Known Activations