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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     land
    -0.07
    atabases
    -0.07
    /dom
    -0.06
     falls
    -0.06
    完
    -0.06
     pronto
    -0.06
     pall
    -0.06
    üss
    -0.06
     appropri
    -0.06
    <!--[
    -0.06
    POSITIVE LOGITS
     आप
    0.07
     halfway
    0.06
     manners
    0.06
    \Service
    0.06
    म
    0.06
    一
    0.06
     مسائل
    0.06
     contends
    0.06
     CONTRACT
    0.06
     ως
    0.06
    Act Density 0.000%

    No Known Activations