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

    Neuronpedia

    INDEX
    Explanations

    dialogue/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Docs
    -0.07
     hanging
    -0.07
    .props
    -0.07
    ящ
    -0.06
     shaking
    -0.06
     naked
    -0.06
    DAT
    -0.06
    .top
    -0.06
     banners
    -0.06
    AWS
    -0.06
    POSITIVE LOGITS
    .Profile
    0.07
    Adjust
    0.07
     Elm
    0.07
    @Entity
    0.06
     Citadel
    0.06
    ");↵
    0.06
     Hurt
    0.06
     Serialize
    0.06
     асп
    0.06
     eclipse
    0.06
    Act Density 0.021%

    No Known Activations