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

    Neuronpedia

    INDEX
    Explanations

    factors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ORY
    -0.07
     saving
    -0.07
     Secondary
    -0.06
    submit
    -0.06
     культури
    -0.06
     発
    -0.06
     ไ
    -0.06
     seeding
    -0.06
    degree
    -0.06
    (drop
    -0.06
    POSITIVE LOGITS
     francais
    0.06
    .randn
    0.06
    =sys
    0.06
     TSR
    0.06
     Semaphore
    0.06
     Savaşı
    0.06
    acus
    0.06
    Family
    0.06
    rál
    0.06
    χία
    0.05
    Act Density 0.036%

    No Known Activations