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

    Neuronpedia

    INDEX
    Explanations

    career aspirations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pungent
    0.43
    िकारक
    0.41
     pebbles
    0.40
     pang
    0.39
    plicial
    0.39
     lembut
    0.38
     milky
    0.38
     Milk
    0.37
     rays
    0.37
    0.37
    POSITIVE LOGITS
     ATM
    0.45
    ATM
    0.42
    바일
    0.41
     IDENT
    0.38
    配信
    0.38
     showc
    0.38
     ISP
    0.37
     테스트
    0.37
     मौ
    0.37
    灞
    0.36
    Act Density 0.000%

    No Known Activations