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

    Neuronpedia

    INDEX
    Explanations

    carve, based, revocation, items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بند
    0.47
    含む
    0.47
     उदा
    0.46
     বি
    0.45
     탄
    0.45
     끝
    0.45
     தொட
    0.44
    𝕣
    0.44
     소재
    0.43
     کمی
    0.43
    POSITIVE LOGITS
    ايا
    0.52
     tejto
    0.52
    Type
    0.52
    洎
    0.52
    Asked
    0.50
     Sumb
    0.49
    ه
    0.49
    تك
    0.48
    чиком
    0.47
    ChatGPT
    0.47
    Act Density 0.000%

    No Known Activations