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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     доз
    -0.06
     explode
    -0.06
     член
    -0.06
    Runnable
    -0.06
     정부
    -0.06
    ि,
    -0.06
    .Note
    -0.06
     ราย
    -0.06
    Species
    -0.06
    ственной
    -0.05
    POSITIVE LOGITS
    .offsetWidth
    0.08
    .base
    0.07
    .tell
    0.06
    lover
    0.06
    (identifier
    0.06
    ()*
    0.06
    encv
    0.06
     Honolulu
    0.06
    uyu
    0.06
    dst
    0.06
    Act Density 0.019%

    No Known Activations