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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     negativity
    -0.06
     cuisine
    -0.06
    診
    -0.06
    驗
    -0.06
     nug
    -0.06
    ман
    -0.06
     chatte
    -0.06
    üny
    -0.06
     переш
    -0.06
    genden
    -0.06
    POSITIVE LOGITS
    .lookup
    0.07
    اورپ
    0.06
     Systems
    0.06
     "../../../
    0.06
    restricted
    0.06
    .epsilon
    0.06
    213
    0.06
    .gamma
    0.06
    REFER
    0.06
     systems
    0.06
    Act Density 0.000%

    No Known Activations