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

    Neuronpedia

    INDEX
    Explanations

    forwarding and relaying information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     মনোযোগ
    0.42
     flores
    0.38
     polo
    0.37
     Blüten
    0.37
     vermeiden
    0.37
    ဓ
    0.37
     avoidance
    0.37
     refining
    0.36
     eficiente
    0.36
     desarroll
    0.35
    POSITIVE LOGITS
     紹介
    0.70
     소개
    0.64
     forwarding
    0.63
     relay
    0.63
     vouch
    0.62
    紹介
    0.61
    介紹
    0.61
    介绍
    0.60
     소개해
    0.59
     relayed
    0.59
    Act Density 0.107%

    No Known Activations