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

    Neuronpedia

    INDEX
    Explanations

    bot instructions/commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ����
    -0.10
     ����
    -0.08
    វិ
    -0.08
    ��������
    -0.08
    chants
    -0.08
    礼包
    -0.08
     imobili
    -0.08
     prêts
    -0.07
     اثر
    -0.07
     epit
    -0.07
    POSITIVE LOGITS
    .ai
    0.10
    .commands
    0.09
     commands
    0.09
    _commands
    0.09
     encouraged
    0.09
     AI
    0.09
     Unlimited
    0.09
     autonomous
    0.08
    .command
    0.08
     silo
    0.08
    Act Density 0.002%

    No Known Activations