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

    Neuronpedia

    INDEX
    Explanations

    terms related to components and configurations in engineering contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    spring contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mitad
    -0.54
     halbe
    -0.54
     moitié
    -0.48
     cuchara
    -0.48
     provisoire
    -0.47
    antaranya
    -0.46
     intellectuelle
    -0.46
     poteva
    -0.45
     sillas
    -0.45
    UnknownFieldSet
    -0.44
    POSITIVE LOGITS
     Spring
    1.09
    Spring
    1.07
     spring
    0.99
     SPRING
    0.94
    spring
    0.91
    SPRING
    0.84
     Primavera
    0.71
     springtime
    0.71
     springing
    0.69
     printemps
    0.68
    Act Density 0.017%

    No Known Activations