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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NSK
    -0.07
    elden
    -0.06
    艺
    -0.06
    google
    -0.06
    cken
    -0.06
    CFG
    -0.06
    _i
    -0.06
    Cancelar
    -0.06
     vk
    -0.05
    _locals
    -0.05
    POSITIVE LOGITS
     then
    0.10
     Then
    0.07
     dann
    0.07
     THEN
    0.07
     serving
    0.07
     затем
    0.06
    ★
    0.06
     Bachelor
    0.06
     удар
    0.06
     emptied
    0.06
    Act Density 0.054%

    No Known Activations