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

    Neuronpedia

    INDEX
    Explanations

    <|end|>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     besser
    -0.09
     Glass
    -0.09
    better
    -0.09
     bessere
    -0.08
     beter
    -0.08
     better
    -0.08
     Better
    -0.08
    Glass
    -0.08
     במיוחד
    -0.07
    _CONN
    -0.07
    POSITIVE LOGITS
     Already
    0.12
     already
    0.12
    already
    0.12
     bereits
    0.12
     bisherigen
    0.12
     già
    0.11
     zaten
    0.11
     ήδη
    0.11
     précédente
    0.11
     bislang
    0.10
    Act Density 0.299%

    No Known Activations