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

    Neuronpedia

    INDEX
    Explanations

    science, food, and non-english concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뻗
    0.44
    μένο
    0.42
    ಡಿಯ
    0.42
    arity
    0.41
    explode
    0.40
    xgb
    0.39
    branchNode
    0.38
     vlog
    0.38
    noj
    0.37
     উপ
    0.37
    POSITIVE LOGITS
     Plantes
    0.48
     Química
    0.46
     Cancer
    0.46
     perdita
    0.46
     Empire
    0.45
     alimentos
    0.44
     தண்ணீர்
    0.44
     Diabetes
    0.44
     perros
    0.44
     alimento
    0.44
    Act Density 0.003%

    No Known Activations