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

    Neuronpedia

    INDEX
    Explanations

    words and phrases dealing with steps in solving a problem such as modeling or insertions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ones
    -0.08
    avigation
    -0.07
    mont
    -0.06
    	volatile
    -0.06
    idad
    -0.06
    ">//
    -0.06
     auditing
    -0.06
    éº
    -0.06
    جÙħ
    -0.06
     Chief
    -0.06
    POSITIVE LOGITS
    /sources
    0.07
    fdc
    0.07
    .library
    0.06
    /classes
    0.06
    Twig
    0.06
     dare
    0.06
    pliers
    0.06
    urum
    0.06
    FromBody
    0.06
    CodeAt
    0.06
    Act Density 0.482%

    No Known Activations