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

    Neuronpedia

    INDEX
    Explanations

    on account

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olgens
    0.40
    शक
    0.38
     गोष्ट
    0.38
     azért
    0.38
     cái
    0.37
     backstory
    0.37
     ईडी
    0.35
    ógico
    0.35
     ofertas
    0.35
    ளிடம்
    0.34
    POSITIVE LOGITS
     account
    0.69
    account
    0.57
     Account
    0.53
     horseback
    0.49
    konto
    0.49
    Account
    0.49
     entering
    0.46
    entering
    0.45
     attaining
    0.43
    アカウント
    0.43
    Act Density 0.006%

    No Known Activations