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

    Neuronpedia

    INDEX
    Explanations

    probability game

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stakeholder
    -0.08
    ��������
    -0.08
     concret
    -0.07
    636
    -0.07
    евич
    -0.07
    ���
    -0.07
    ্�
    -0.07
    ��
    -0.07
    139
    -0.07
    ����
    -0.07
    POSITIVE LOGITS
     retries
    0.10
     മരണ
    0.09
     probabilities
    0.09
    �
    0.09
    Retries
    0.09
     morrer
    0.09
     deferred
    0.08
    κος
    0.08
     delaying
    0.08
     Deferred
    0.08
    Act Density 0.014%

    No Known Activations