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

    Neuronpedia

    INDEX
    Explanations

    importance followed by clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Detail
    0.37
     southern
    0.36
    "></
    0.35
     brunes
    0.34
    GD
    0.33
    нут
    0.32
    并将
    0.32
    Sav
    0.32
     vět
    0.32
     testaceis
    0.31
    POSITIVE LOGITS
     bahwa
    0.79
     أن
    0.77
     να
    0.68
     أنه
    0.65
     that
    0.65
     ότι
    0.64
     dass
    0.62
     että
    0.61
     rằng
    0.61
     bahawa
    0.59
    Act Density 0.022%

    No Known Activations