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

    Neuronpedia

    INDEX
    Explanations

    sounds or vocalisations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     este
    0.45
     Edith
    0.41
     ос
    0.38
    icia
    0.38
     seat
    0.38
    est
    0.37
    Os
    0.37
    amped
    0.37
    set
    0.37
    רום
    0.37
    POSITIVE LOGITS
     Uz
    0.49
     hz
    0.42
    Uz
    0.41
     بت
    0.39
    "{@
    0.39
     publiés
    0.38
     '/'
    0.38
     যের
    0.38
    鳧
    0.37
     बढ़ावा
    0.37
    Act Density 0.000%

    No Known Activations