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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     %#
    -0.08
     combinations
    -0.08
     knobs
    -0.07
    おすすめ
    -0.07
     recommendations
    -0.07
     liking
    -0.07
     Chesapeake
    -0.07
     knowledge
    -0.07
     dizziness
    -0.07
    əz
    -0.07
    POSITIVE LOGITS
     ausgestattet
    0.09
    -like
    0.09
     Möglichkeit
    0.08
     namens
    0.08
    在那里
    0.08
     nestled
    0.08
     rud
    0.08
     صغير
    0.08
     daneben
    0.08
     Bene
    0.07
    Act Density 0.147%

    No Known Activations