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

    Neuronpedia

    INDEX
    Explanations

    concept aims and formation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kleines
    -1.19
    觀察
    -1.02
    Carrito
    -1.00
     típica
    -0.98
    常見
    -0.97
    栳
    -0.97
     bisschen
    -0.96
     microcontroller
    -0.94
     sposob
    -0.94
     comprised
    -0.94
    POSITIVE LOGITS
    concept
    2.27
     Concept
    2.06
    concepts
    2.03
    Concept
    1.90
     concept
    1.90
     concepts
    1.64
     conceptual
    1.59
     Concepts
    1.56
     concepto
    1.55
    CONCEPT
    1.55
    Act Density 0.015%

    No Known Activations