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

    Neuronpedia

    INDEX
    Explanations

    could

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    man
    -0.08
     partisan
    -0.07
     maken
    -0.07
     specified
    -0.07
    An
    -0.06
    shape
    -0.06
    АН
    -0.06
     debe
    -0.06
    title
    -0.06
    rama
    -0.06
    POSITIVE LOGITS
     could
    0.10
     Could
    0.08
    could
    0.07
    CID
    0.07
    coc
    0.07
     Took
    0.07
     отдел
    0.07
     �
    0.07
     coping
    0.07
    ักก
    0.07
    Act Density 0.086%

    No Known Activations