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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    base
    -0.07
     jurisdictions
    -0.06
    Hallo
    -0.06
     Cyril
    -0.06
    osaic
    -0.06
    Creat
    -0.06
     Dubai
    -0.06
     amer
    -0.06
    ystatechange
    -0.06
    焦
    -0.06
    POSITIVE LOGITS
     esk
    0.07
     refunded
    0.07
    */
    0.06
     NIL
    0.06
    /report
    0.06
     buz
    0.06
     faded
    0.06
     blending
    0.06
     bare
    0.06
     sıra
    0.06
    Act Density 0.029%

    No Known Activations