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

    Neuronpedia

    INDEX
    Explanations

    evolutionary divergence and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Immediately
    0.75
    Immediately
    0.70
     possèdent
    0.68
     ചുമ
    0.67
     unmittelbar
    0.65
     détails
    0.64
     mengetahui
    0.63
    guessed
    0.63
     hük
    0.62
     Execute
    0.62
    POSITIVE LOGITS
     transformation
    2.25
     shift
    2.20
     shifts
    2.05
     transformations
    1.98
    transformation
    1.94
     Transformation
    1.87
    shift
    1.84
     evolution
    1.83
     change
    1.80
     metamorphosis
    1.80
    Act Density 0.621%

    No Known Activations