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

    Neuronpedia

    INDEX
    Explanations

    Prepositional phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     geleverd
    -0.08
    ize
    -0.08
    n't
    -0.08
    рение
    -0.08
     ingeb
    -0.08
     uitgebreid
    -0.07
     gestart
    -0.07
     toegestaan
    -0.07
    qrt
    -0.07
     vlo
    -0.07
    POSITIVE LOGITS
     pozost
    0.11
    留下
    0.10
     dudas
    0.10
     puzzled
    0.09
     unanswered
    0.09
     kvar
    0.09
     bırak
    0.09
     silẹ
    0.09
     باقی
    0.09
     залиш
    0.09
    Act Density 0.057%

    No Known Activations