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

    Neuronpedia

    INDEX
    Explanations

    wait

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    相比于
    -0.08
    ields
    -0.07
     Feder
    -0.07
    .getS
    -0.07
     Cry
    -0.07
    burg
    -0.06
    ols
    -0.06
     Educ
    -0.06
     sind
    -0.06
    .fold
    -0.06
    POSITIVE LOGITS
    船只
    0.07
     машин
    0.07
     location
    0.07
    patient
    0.07
    ائم
    0.07
     lieu
    0.07
    =.
    0.06
     proceeded
    0.06
     hailed
    0.06
     vi
    0.06
    Act Density 0.001%

    No Known Activations