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

    Neuronpedia

    INDEX
    Explanations

    the word again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nearest
    0.44
    urón
    0.43
     closest
    0.43
     nearest
    0.42
     Rhino
    0.41
    탔
    0.41
     CRM
    0.39
     Vocês
    0.39
     KYC
    0.39
     frühen
    0.39
    POSITIVE LOGITS
     similarly
    0.54
     likewise
    0.48
    Similarly
    0.47
    こちらも
    0.46
    டும்
    0.45
     גם
    0.44
    addAnimation
    0.44
     Similarly
    0.41
    Summary
    0.41
    也可以
    0.40
    Act Density 0.002%

    No Known Activations