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

    Neuronpedia

    INDEX
    Explanations

    large numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    29
    -0.09
    14
    -0.08
    134
    -0.08
    25
    -0.08
    51
    -0.08
    168
    -0.08
    10
    -0.08
    17
    -0.07
    23
    -0.07
    35
    -0.07
    POSITIVE LOGITS
    ('<?
    0.07
     истории
    0.06
     iNdEx
    0.06
     hồ
    0.06
    れている
    0.06
    поч
    0.06
    0.06
     persecuted
    0.06
     методи
    0.06
    BoundingBox
    0.06
    Act Density 0.150%

    No Known Activations