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

    Neuronpedia

    INDEX
    Explanations

    random internet text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    교육
    -0.07
     shattered
    -0.07
     Cond
    -0.07
    lığ
    -0.07
    光
    -0.06
    hour
    -0.06
    資
    -0.06
     WEB
    -0.06
    .writeFile
    -0.06
    Associate
    -0.06
    POSITIVE LOGITS
    (URL
    0.07
    (map
    0.06
    _sphere
    0.06
    /messages
    0.06
     =~
    0.06
     كام
    0.06
    }{
    0.06
    /operator
    0.06
     sağlamak
    0.06
     spont
    0.06
    Act Density 0.000%

    No Known Activations