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

    Neuronpedia

    INDEX
    Explanations

    code assignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    جا
    -0.07
     famous
    -0.07
     jours
    -0.07
     BSD
    -0.06
    办
    -0.06
     tritur
    -0.06
     Craw
    -0.06
    �
    -0.06
    entreprise
    -0.06
    Ja
    -0.06
    POSITIVE LOGITS
     GIT
    0.07
    ({},
    0.06
    immune
    0.06
    (m
    0.06
     committing
    0.06
    (skill
    0.06
    .Iterator
    0.06
    )throws
    0.06
     ^(
    0.06
    .cookies
    0.06
    Act Density 0.008%

    No Known Activations