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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SQUARE
    -0.07
     Square
    -0.07
     яку
    -0.06
     interrupted
    -0.06
     Turing
    -0.06
     Permanent
    -0.06
    =\
    -0.06
    Medium
    -0.06
     startled
    -0.06
    ')
↵
    -0.06
    POSITIVE LOGITS
     ราย
    0.06
    ώς
    0.06
    ấy
    0.06
    αιδ
    0.06
     fotoğraf
    0.06
    кет
    0.06
     obesity
    0.06
     acceptance
    0.06
    主人
    0.06
    �
    0.06
    Act Density 0.031%

    No Known Activations