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

    Neuronpedia

    INDEX
    Explanations

    Terraform or metformin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    1.28
     I
    1.13
    ur
    1.09
    に
    1.09
    h
    1.05
    it
    0.97
    um
    0.95
    al
    0.87
    ing
    0.87
    ৭
    0.87
    POSITIVE LOGITS
    IN
    0.85
    ların
    0.80
     السعود
    0.79
    ’,
    0.78
    ,’
    0.78
     is
    0.78
    كب
    0.77
     הראש
    0.77
     betekent
    0.77
    )
    0.76
    Act Density 0.009%

    No Known Activations