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

    Neuronpedia

    INDEX
    Explanations

    Numbers starting with 501/401

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $img
    -0.07
     kvinne
    -0.07
    ERS
    -0.07
     nelze
    -0.07
    цять
    -0.07
     xx
    -0.07
     kern
    -0.07
    =add
    -0.06
     gắn
    -0.06
     изображ
    -0.06
    POSITIVE LOGITS
    401
    0.13
    801
    0.12
    501
    0.12
    601
    0.11
    301
    0.11
    901
    0.10
    701
    0.10
    203
    0.10
    101
    0.10
    503
    0.10
    Act Density 0.044%

    No Known Activations