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

    Neuronpedia

    INDEX
    Explanations

    limited order buying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imètre
    0.50
    onnées
    0.47
    НІ
    0.46
     måde
    0.46
    ੦
    0.46
    cèle
    0.45
    inguém
    0.44
    Enabled
    0.44
    utente
    0.43
    uting
    0.43
    POSITIVE LOGITS
     Technician
    0.49
    ب
    0.49
     due
    0.47
     chevron
    0.47
     assertTrue
    0.46
     accom
    0.45
    ले
    0.44
     Upan
    0.42
    ли
    0.42
    ל
    0.42
    Act Density 0.000%

    No Known Activations