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

    Neuronpedia

    INDEX
    Explanations

    meeting scheduling, attendance, atmosphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻧ
    0.91
    тку
    0.83
     calific
    0.80
     يع
    0.77
     nettoy
    0.75
    ﻳ
    0.75
     marqués
    0.75
     berichten
    0.75
    로
    0.74
     اين
    0.73
    POSITIVE LOGITS
    ため
    0.92
    E
    0.90
    A
    0.89
    ;
    0.84
    ،
    0.83
    ad
    0.81
     meet
    0.81
    day
    0.80
    sts
    0.80
    ।
    0.80
    Act Density 0.015%

    No Known Activations