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

    Neuronpedia

    INDEX
    Explanations

    post

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    韭
    -0.07
    �
    -0.07
    temps
    -0.07
    海域
    -0.06
    mate
    -0.06
     sin
    -0.06
     Bey
    -0.06
    狝
    -0.06
    lette
    -0.06
    Elf
    -0.06
    POSITIVE LOGITS
     paced
    0.07
     WHILE
    0.07
     foundation
    0.07
     parsley
    0.07
     Bread
    0.07
     Instit
    0.07
    .Abs
    0.06
     basename
    0.06
    林业
    0.06
     sender
    0.06
    Act Density 0.006%

    No Known Activations