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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dropdown
    -0.07
     stability
    -0.07
     intoxicated
    -0.07
     time
    -0.07
    excerpt
    -0.07
     graduates
    -0.07
     IV
    -0.07
    flex
    -0.06
     simplified
    -0.06
     exemptions
    -0.06
    POSITIVE LOGITS
     ulož
    0.07
    .ping
    0.06
    .mixer
    0.06
    __)↵↵
    0.06
    ",__
    0.06
    ),
↵
    0.06
    .Syntax
    0.06
    __)↵↵↵
    0.06
    rug
    0.06
    _InternalArray
    0.06
    Act Density 0.024%

    No Known Activations