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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     histor
    -0.06
    侯
    -0.06
     phù
    -0.06
     vibe
    -0.06
    Speed
    -0.06
    -packages
    -0.06
    mean
    -0.06
    Bean
    -0.06
    curr
    -0.06
    sp
    -0.06
    POSITIVE LOGITS
    ='')↵
    0.07
     Bom
    0.06
    ač
    0.06
    -element
    0.06
    ΙΤ
    0.06
    Epoch
    0.06
    lerce
    0.06
     produkt
    0.06
     открыт
    0.06
    --*/↵
    0.06
    Act Density 0.004%

    No Known Activations