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

    Neuronpedia

    INDEX
    Explanations

    partnerships and collaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    1.09
     bref
    0.92
     raisons
    0.91
     sév
    0.91
    boton
    0.84
     horrific
    0.84
     bệnh
    0.83
     martini
    0.83
    ซ์
    0.82
     haunting
    0.80
    POSITIVE LOGITS
    夥伴
    1.13
    ون
    1.07
    合作
    0.98
     colabor
    0.93
     spolupr
    0.93
     осуществля
    0.93
    িত্ব
    0.90
    ви
    0.89
    ASI
    0.88
     колле
    0.86
    Act Density 0.166%

    No Known Activations