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

    Neuronpedia

    INDEX
    Explanations

    code headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kim
    -0.07
    .mp
    -0.06
     right
    -0.06
     fracture
    -0.06
    -hours
    -0.06
     gave
    -0.06
    	my
    -0.06
    Ali
    -0.06
     Variety
    -0.06
    _daily
    -0.06
    POSITIVE LOGITS
    0.07
    ічні
    0.07
     이를
    0.07
    erusform
    0.06
    ecast
    0.06
    포
    0.06
     knull
    0.06
    landa
    0.06
    ��
    0.06
     wordpress
    0.06
    Act Density 0.001%

    No Known Activations