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

    Neuronpedia

    INDEX
    Explanations

    refinement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    实在
    -0.07
     �
    -0.07
     之
    -0.07
     communicates
    -0.06
     leftovers
    -0.06
    .AspNet
    -0.06
     cdr
    -0.06
    偏
    -0.06
    _DIS
    -0.06
    acement
    -0.06
    POSITIVE LOGITS
    /blog
    0.06
    (interface
    0.06
    \AppData
    0.06
    isinde
    0.06
     Businesses
    0.06
     bele
    0.06
    的是
    0.06
    ","#
    0.06
    afe
    0.06
     فو
    0.06
    Act Density 0.000%

    No Known Activations