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

    Neuronpedia

    INDEX
    Explanations

    Zeroes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Sqrt
    -0.06
    去
    -0.06
     CEL
    -0.06
    othy
    -0.06
     E
    -0.06
    ühr
    -0.06
     maur
    -0.06
    释
    -0.06
    َد
    -0.06
    okableCall
    -0.06
    POSITIVE LOGITS
     nuestras
    0.07
     outros
    0.07
    ちゃん
    0.07
    -flight
    0.07
     modifier
    0.07
     grabbing
    0.06
    lit
    0.06
    .preview
    0.06
    -Owned
    0.06
     преступ
    0.06
    Act Density 0.031%

    No Known Activations