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

    Neuronpedia

    INDEX
    Explanations

    contains the word "английский"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    имого
    -0.08
    ，其中
    -0.08
    龙江
    -0.08
     sul
    -0.08
    。此外
    -0.08
    。然而
    -0.07
     修改
    -0.07
     articulated
    -0.07
     Frontier
    -0.07
    iedo
    -0.07
    POSITIVE LOGITS
     correcto
    0.08
     castell
    0.08
     bä
    0.08
    portable
    0.08
    -remove
    0.07
     correcta
    0.07
     Consent
    0.07
     tum
    0.07
     Amma
    0.07
    ppa
    0.07
    Act Density 0.004%

    No Known Activations