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

    Neuronpedia

    INDEX
    Explanations

    f

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ',
↵
    -0.07
     stands
    -0.07
     rfl
    -0.06
     yours
    -0.06
     Banco
    -0.06
    दम
    -0.06
     symbols
    -0.06
     plugins
    -0.06
     Murray
    -0.06
     rendering
    -0.06
    POSITIVE LOGITS
    ungen
    0.06
     статьи
    0.06
    GroupId
    0.06
    conti
    0.06
    .vstack
    0.06
     endIndex
    0.06
    tright
    0.06
     Sega
    0.06
     قطر
    0.06
     (�
    0.06
    Act Density 0.003%

    No Known Activations