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

    Neuronpedia

    INDEX
    Explanations

    generating lists of ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     переменную
    0.71
    semantics
    0.70
     प्रणाली
    0.70
     दौरा
    0.69
     componente
    0.68
     শব্দটি
    0.68
     complejo
    0.68
    ponente
    0.68
    transmission
    0.67
     complesso
    0.67
    POSITIVE LOGITS
     suggestions
    2.05
     ideas
    2.04
     ways
    1.94
     tips
    1.85
     Ways
    1.77
     recipes
    1.75
     Ideas
    1.72
    Ways
    1.66
     alternatives
    1.65
     Tips
    1.63
    Act Density 1.259%

    No Known Activations