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

    Neuronpedia

    INDEX
    Explanations

    provided for educational purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     regiments
    0.43
     regra
    0.41
    acht
    0.40
     regiment
    0.40
     annealing
    0.39
    ക്കുറിച്ച്
    0.38
     substituent
    0.38
    berapa
    0.38
     regras
    0.37
    regel
    0.37
    POSITIVE LOGITS
     purely
    0.84
     educational
    0.75
    Educational
    0.72
    あくまで
    0.68
    好奇
    0.66
    Knowledge
    0.64
     informational
    0.63
    educational
    0.63
     Knowledge
    0.62
     curiosity
    0.62
    Act Density 0.016%

    No Known Activations