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

    Neuronpedia

    INDEX
    Explanations

    how she talks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utenti
    0.51
     futuro
    0.49
     trei
    0.47
     spirito
    0.47
     предприя
    0.46
    users
    0.46
     tiga
    0.46
    tipo
    0.46
     użytk
    0.45
     tradizione
    0.44
    POSITIVE LOGITS
    ⋙
    0.54
    ッド
    0.44
     বিরক্ত
    0.44
    看法
    0.42
     blasts
    0.40
    ový
    0.39
    >
    0.39
    Callories
    0.39
     negatively
    0.39
    ومة
    0.38
    Act Density 0.002%

    No Known Activations