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

    Neuronpedia

    INDEX
    Explanations

    slowly, existing, increased

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    চরিত
    0.49
    ことです
    0.44
     চৈতন্ত
    0.44
    isations
    0.43
     चेंजेस
    0.43
    isés
    0.43
    粉絲
    0.43
     haloes
    0.42
    ítás
    0.42
    椏
    0.42
    POSITIVE LOGITS
    </h3>
    0.49
    ρικ
    0.44
    cija
    0.43
    </h2>
    0.42
     slowly
    0.42
     धीरे
    0.40
    endente
    0.40
     могла
    0.40
    acak
    0.39
     pastel
    0.39
    Act Density 0.000%

    No Known Activations