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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Marc
    -0.07
    。（
    -0.07
     Laos
    -0.07
    Other
    -0.06
    model
    -0.06
    �
    -0.06
     camps
    -0.06
    aman
    -0.06
     hodnot
    -0.06
    ereotype
    -0.06
    POSITIVE LOGITS
     infused
    0.06
     čast
    0.06
     любой
    0.06
     inode
    0.06
     olmadığı
    0.06
    μι
    0.06
     trục
    0.06
    のように
    0.06
    appeared
    0.06
    μί
    0.06
    Act Density 0.000%

    No Known Activations