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

    Neuronpedia

    INDEX
    Explanations

    Length and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    末
    -0.07
     {{--
    -0.07
     resting
    -0.07
    无偿
    -0.07
     nal
    -0.07
    何
    -0.07
     her
    -0.07
     _
    -0.07
     Zimbabwe
    -0.07
    ころ
    -0.07
    POSITIVE LOGITS
    máticos
    0.08
    מקומות
    0.07
    >>>>>>>>
    0.07
     KNOW
    0.07
    车型
    0.07
    isd
    0.07
    Know
    0.07
    PARTMENT
    0.07
    ‾
    0.07
    مشاكل
    0.07
    Act Density 0.008%

    No Known Activations