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

    Neuronpedia

    INDEX
    Explanations

    written content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Corm
    -0.07
     Stephen
    -0.06
    ин
    -0.06
     regimen
    -0.06
    िव
    -0.06
     Checker
    -0.06
     Second
    -0.06
     Compound
    -0.06
     carne
    -0.06
     FALSE
    -0.06
    POSITIVE LOGITS
    (Mouse
    0.07
    beits
    0.07
     ๆ
    0.07
    (passport
    0.06
     delivers
    0.06
    ๆ
    0.06
     attempt
    0.06
    /ws
    0.06
    (store
    0.06
     nave
    0.06
    Act Density 0.011%

    No Known Activations