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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =message
    -0.07
     thời
    -0.07
     Positive
    -0.06
     Instantiate
    -0.06
    (CON
    -0.06
     "./
    -0.06
     Baton
    -0.06
     multic
    -0.06
     estão
    -0.06
     пласти
    -0.06
    POSITIVE LOGITS
     „
    0.07
    ώ
    0.06
    Friends
    0.06
    保
    0.06
    （
    0.06
    antino
    0.06
     cur
    0.06
    把
    0.06
    IBUTE
    0.06
     blitz
    0.06
    Act Density 0.015%

    No Known Activations