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

    Neuronpedia

    INDEX
    Explanations

    various verb conjugations in languages other than English

    oai_token-act-pair · gemini-2.0-flash

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.57
    complexContent
    -0.54
    enek
    -0.52
     doInBackground
    -0.51
     ModelExpression
    -0.51
     boxer
    -0.50
    monių
    -0.49
     betweenstory
    -0.47
    bourhood
    -0.47
    yeezy
    -0.45
    POSITIVE LOGITS
     will
    0.77
    will
    0.71
     prochain
    0.68
     nantinya
    0.67
     sẽ
    0.66
     youll
    0.66
     nanti
    0.65
     tomorrow
    0.65
     esternos
    0.63
    Will
    0.61
    Act Density 0.784%

    No Known Activations