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

    Neuronpedia

    INDEX
    Explanations

    completion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الشمس
    -0.08
     behandeld
    -0.07
     Pela
    -0.07
    .MM
    -0.07
     MPs
    -0.07
    ource
    -0.07
     sépar
    -0.07
     combatt
    -0.07
    source
    -0.07
     starving
    -0.07
    POSITIVE LOGITS
    เติม
    0.12
     compléter
    0.12
     completar
    0.11
     completing
    0.11
     ergänzt
    0.11
     ergän
    0.10
     complemento
    0.09
    补
    0.09
     строки
    0.09
     Ergän
    0.09
    Act Density 0.026%

    No Known Activations