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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     khô
    -0.07
     version
    -0.07
     unavoid
    -0.07
    rama
    -0.06
    aju
    -0.06
     genuinely
    -0.06
     Lamar
    -0.06
    -REAL
    -0.06
     rằng
    -0.06
     reservation
    -0.06
    POSITIVE LOGITS
     pozdě
    0.06
    .Dropout
    0.06
    过程
    0.06
     pains
    0.06
     Μαρ
    0.06
    .figure
    0.06
     жест
    0.06
    ££
    0.06
    (userName
    0.06
     allele
    0.06
    Act Density 0.042%

    No Known Activations