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

    Neuronpedia

    INDEX
    Explanations

    main

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Filter
    -0.07
     perspective
    -0.07
    سن
    -0.06
     Sek
    -0.06
    cil
    -0.06
     voxel
    -0.06
     себ
    -0.06
    ёт
    -0.06
    _survey
    -0.06
    ศร
    -0.06
    POSITIVE LOGITS
    \common
    0.07
    -paced
    0.07
    (Long
    0.06
    .Long
    0.06
    .dp
    0.06
     обличчя
    0.06
    ่ได
    0.06
    �
    0.06
    (lista
    0.06
    ลง
    0.06
    Act Density 0.006%

    No Known Activations