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

    Neuronpedia

    INDEX
    Explanations

    mechanical components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     او
    -0.07
    GENERAL
    -0.07
    рам
    -0.07
    rust
    -0.06
    cu
    -0.06
     Gson
    -0.06
     guise
    -0.06
     BÖL
    -0.06
    γορ
    -0.06
     tir
    -0.06
    POSITIVE LOGITS
    deniz
    0.07
    /topic
    0.07
     ########.
    0.06
    ＿＿
    0.06
    restart
    0.06
     науков
    0.06
     воспал
    0.06
    ＿＿＿＿
    0.06
     Beatles
    0.06
    .want
    0.06
    Act Density 0.040%

    No Known Activations