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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mayacak
    -0.06
    َان
    -0.06
     وسی
    -0.06
    POL
    -0.06
    astery
    -0.06
     Hence
    -0.06
     Species
    -0.06
    theorem
    -0.06
     Alec
    -0.06
    commend
    -0.06
    POSITIVE LOGITS
    proxy
    0.08
     Long
    0.07
    .Kind
    0.07
    cerr
    0.06
    ItemClick
    0.06
    션
    0.06
    ไฟล
    0.06
    .UR
    0.06
    {//
    0.06
     longing
    0.06
    Act Density 0.000%

    No Known Activations