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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parola
    0.46
    ኛውም
    0.45
     visiteurs
    0.45
    idać
    0.45
     fica
    0.45
     espécie
    0.45
     camisetas
    0.44
     princípio
    0.44
     ไว้
    0.43
     அப்படி
    0.43
    POSITIVE LOGITS
    \
    0.57
    0.53
    {
    0.50
    }
    0.49
    (
    0.46
    +
    0.44
    of
    0.42
       
    0.41
     this
    0.41
                
    0.40
    Act Density 0.048%

    No Known Activations