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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     돌
    -0.07
     Brno
    -0.07
    �
    -0.06
    Below
    -0.06
    猪
    -0.06
    Ids
    -0.06
    iydi
    -0.06
     یون
    -0.06
    loub
    -0.06
    -ref
    -0.06
    POSITIVE LOGITS
     coax
    0.08
    _style
    0.07
     evangelical
    0.07
    atto
    0.06
     +↵↵
    0.06
     благод
    0.06
     이벤트
    0.06
    reflection
    0.06
     aiding
    0.06
    .Extensions
    0.06
    Act Density 0.001%

    No Known Activations