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

    Neuronpedia

    INDEX
    Explanations

    classical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Attach
    -0.07
     svět
    -0.06
     shepherd
    -0.06
     chained
    -0.06
    -metadata
    -0.06
     badge
    -0.06
     băng
    -0.06
     gras
    -0.06
     Actions
    -0.06
    Anywhere
    -0.06
    POSITIVE LOGITS
    -interface
    0.06
    bios
    0.06
    ]");↵
    0.06
     downtime
    0.06
     eb
    0.06
    現
    0.06
     �
    0.06
    ORM
    0.06
    рад
    0.06
    ісля
    0.06
    Act Density 0.032%

    No Known Activations