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

    Neuronpedia

    INDEX
    Explanations

    billing, code, pirates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.53
    id
    1.35
     vão
    1.26
    io
    1.19
    là
    1.16
    पूर्ण
    1.16
    iovascular
    1.11
    ר
    1.01
    wood
    1.00
    âmica
    1.00
    POSITIVE LOGITS
    щими
    1.26
    выми
    1.17
     bargain
    1.16
    тивными
    1.13
    ोरेशन
    1.12
    1.09
     pirates
    1.07
    κ
    1.06
     pirate
    1.05
    tting
    1.05
    Act Density 0.000%

    No Known Activations