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

    Neuronpedia

    INDEX
    Explanations

    comma and one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     redesign
    -0.07
    Convert
    -0.07
    .tail
    -0.07
    ibia
    -0.06
    dığ
    -0.06
     |=
    -0.06
    [from
    -0.06
    evaluate
    -0.06
     redesigned
    -0.06
    POSITIVE LOGITS
     endured
    0.07
    ーニ
    0.07
     klas
    0.06
     кін
    0.06
     символ
    0.06
     japon
    0.06
    odynamics
    0.06
     serum
    0.06
     النس
    0.06
    embre
    0.06
    Act Density 0.015%

    No Known Activations