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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Width
    -0.07
    ็กซ
    -0.07
     feeling
    -0.06
     ALSO
    -0.06
     fid
    -0.06
    catalog
    -0.06
     lẽ
    -0.06
     gains
    -0.06
    قام
    -0.06
    работ
    -0.06
    POSITIVE LOGITS
    宙
    0.07
    502
    0.06
     науч
    0.06
    �
    0.06
     domest
    0.06
    Nil
    0.06
    ior
    0.06
    _ability
    0.06
     Zukunft
    0.06
    tie
    0.06
    Act Density 0.006%

    No Known Activations