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

    Neuronpedia

    INDEX
    Explanations

    development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quivo
    -0.07
    冷
    -0.07
    ives
    -0.06
     segments
    -0.06
    (Syntax
    -0.06
     sandbox
    -0.06
    enda
    -0.06
    寒
    -0.06
    IEWS
    -0.06
    údo
    -0.06
    POSITIVE LOGITS
     systemd
    0.07
     ef
    0.06
    hexdigest
    0.06
     Dove
    0.06
     sinon
    0.06
    ,start
    0.06
    disciplinary
    0.06
     newValue
    0.06
     ध
    0.06
     मर
    0.06
    Act Density 0.017%

    No Known Activations