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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ToLower
    -0.07
    endez
    -0.07
    ULL
    -0.07
    ruba
    -0.06
     troubling
    -0.06
     offence
    -0.06
    _lua
    -0.06
     ammunition
    -0.06
    960
    -0.06
    cy
    -0.06
    POSITIVE LOGITS
     νεφοκάλυψης
    0.07
    ButtonTitles
    0.07
     전용면적
    0.06
     กำ
    0.06
     stages
    0.06
    .GetFiles
    0.06
     eject
    0.06
     فرمود
    0.06
    accessToken
    0.06
    olatile
    0.06
    Act Density 0.000%

    No Known Activations