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

    Neuronpedia

    INDEX
    Explanations

    istr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     يول
    -0.08
    ㅇ
    -0.07
     missing
    -0.07
    包包
    -0.07
    g
    -0.07
    kek
    -0.07
    antro
    -0.07
     nei
    -0.07
    佑
    -0.07
     שי
    -0.07
    POSITIVE LOGITS
     ledge
    0.08
    专场
    0.08
     expedition
    0.08
     aplic
    0.07
     Eb
    0.07
    竞价
    0.07
    答辩
    0.06
    (Bit
    0.06
    _pt
    0.06
     bonded
    0.06
    Act Density 0.000%

    No Known Activations