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

    Neuronpedia

    INDEX
    Explanations

    Verb "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rst
    -0.07
    ्रथ
    -0.07
     kW
    -0.07
    -bg
    -0.07
     степ
    -0.07
     condos
    -0.07
    uae
    -0.07
    ूद
    -0.06
    iting
    -0.06
    (range
    -0.06
    POSITIVE LOGITS
    Calls
    0.06
    -century
    0.06
    вад
    0.06
    帖
    0.05
     �
    0.05
    .""
    0.05
    )↵↵↵↵
    0.05
     Hok
    0.05
     Reco
    0.05
     princes
    0.05
    Act Density 0.078%

    No Known Activations