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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    -1.77
    to
    -1.77
     
    -1.68
    is
    -1.59
    in
    -1.54
    un
    -1.52
    ra
    -1.51
    ma
    -1.50
    ar
    -1.46
    </h5>
    -1.41
    POSITIVE LOGITS
     ujar
    1.69
     maksi
    1.62
    咘
    1.61
     menek
    1.54
     kutu
    1.53
     parfüm
    1.52
     seksi
    1.50
     salg
    1.48
    Allez
    1.48
     kupa
    1.45
    Act Density 0.029%

    No Known Activations