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

    Neuronpedia

    INDEX
    Explanations

    Numerical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ter
    -0.07
     technically
    -0.07
    arn
    -0.07
    (T
    -0.07
    ථ
    -0.07
     tè
    -0.07
     арнал
    -0.07
     spécialiste
    -0.07
    ular
    -0.06
     inher
    -0.06
    POSITIVE LOGITS
     ఇప్పటికే
    0.10
     bereits
    0.10
     muiden
    0.09
    already
    0.09
     Already
    0.09
    已有
    0.09
     제외
    0.09
     já
    0.09
     déjà
    0.08
     già
    0.08
    Act Density 0.181%

    No Known Activations