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

    Neuronpedia

    INDEX
    Explanations

    Period token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     обеспеч
    -0.07
     respects
    -0.07
    -room
    -0.07
    餍
    -0.07
    膙
    -0.07
    reature
    -0.06
    Otherwise
    -0.06
     "../
    -0.06
    𝕮
    -0.06
    Authorities
    -0.06
    POSITIVE LOGITS
     quieter
    0.07
    /forms
    0.07
     mound
    0.06
    告诉你
    0.06
    냄
    0.06
    enez
    0.06
     lowest
    0.06
     vå
    0.06
     detachment
    0.06
     Each
    0.06
    Act Density 0.004%

    No Known Activations