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

    Neuronpedia

    INDEX
    Explanations

    free verse poem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ି
    0.90
    阮
    0.84
     gras
    0.79
    𝑎
    0.79
    à
    0.79
    å
    0.78
     amply
    0.77
     Ceb
    0.76
     پاورپوینت
    0.75
     të
    0.75
    POSITIVE LOGITS
    وط
    0.87
     Textured
    0.85
    लैंड
    0.85
    amientos
    0.82
    overnment
    0.80
     inferiores
    0.80
    ificates
    0.79
    歌詞
    0.79
    Error
    0.78
    nungen
    0.78
    Act Density 0.001%

    No Known Activations