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

    Neuronpedia

    INDEX
    Explanations

    configuration snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ionized
    0.45
     molten
    0.42
     dumbbells
    0.42
     Alex
    0.41
     Glen
    0.41
     transducer
    0.39
     conformal
    0.38
     pyrr
    0.38
     Oliv
    0.38
     orbiting
    0.38
    POSITIVE LOGITS
    tags
    0.64
    variables
    0.54
    Tags
    0.50
    dependencies
    0.48
    requirements
    0.47
    Variables
    0.46
    prestations
    0.45
    ustom
    0.44
    extras
    0.44
    options
    0.44
    Act Density 0.021%

    No Known Activations