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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     루
    -0.07
     들
    -0.06
    」の
    -0.06
     Bbw
    -0.06
     convict
    -0.06
     обс
    -0.06
     이유
    -0.06
    ánt
    -0.06
    діл
    -0.06
    риф
    -0.06
    POSITIVE LOGITS
     dehydration
    0.07
     slim
    0.07
    THEN
    0.07
    ight
    0.07
    odafone
    0.06
     contraction
    0.06
     functional
    0.06
     deviceId
    0.06
     LGBT
    0.06
    .URL
    0.06
    Act Density 0.027%

    No Known Activations