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
     backyard
    -0.07
     Significant
    -0.07
    urus
    -0.06
     detectives
    -0.06
    izado
    -0.06
     spanning
    -0.06
     Great
    -0.06
    ่อน
    -0.06
    AF
    -0.06
     Brendan
    -0.06
    POSITIVE LOGITS
     ())
    0.07
     kell
    0.07
    [((
    0.06
    .:.:.:.
    0.06
    @
    0.06
     syll
    0.06
    METHOD
    0.06
    .shiro
    0.06
     olup
    0.06
     doi
    0.06
    Act Density 0.368%

    No Known Activations