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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beckham
    -0.07
     Phillips
    -0.06
     gerade
    -0.06
    сен
    -0.06
     aviation
    -0.06
     emojis
    -0.06
     Mata
    -0.06
    telegram
    -0.06
    :B
    -0.06
     benzer
    -0.06
    POSITIVE LOGITS
    pf
    0.07
     tud
    0.07
    功
    0.06
     ου
    0.06
    ,､
    0.06
     Gal
    0.06
     vulnerabilities
    0.06
    OURS
    0.06
     элем
    0.06
    powers
    0.06
    Act Density 0.038%

    No Known Activations