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

    Neuronpedia

    INDEX
    Explanations

    scams and manipulation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     фирм
    -0.07
     gestión
    -0.07
    信息披露
    -0.07
     oversight
    -0.06
    _corr
    -0.06
    Mes
    -0.06
     preacher
    -0.06
     ide
    -0.06
    مار
    -0.06
    同胞
    -0.06
    POSITIVE LOGITS
    VRTX
    0.07
     Voll
    0.07
    bundles
    0.07
     cleaned
    0.07
    쯔
    0.07
     CG
    0.07
     Colomb
    0.07
    摇了
    0.07
     Hait
    0.07
     GCBO
    0.06
    Act Density 0.011%

    No Known Activations