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

    Neuronpedia

    INDEX
    Explanations

    Android menu creation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UserInfo
    -0.06
    plusplus
    -0.06
     Kramer
    -0.06
    122
    -0.06
    (pat
    -0.06
    }';↵
    -0.06
    ```
    -0.06
    宜
    -0.05
    、新
    -0.05
    .nl
    -0.05
    POSITIVE LOGITS
    ��
    0.07
    -life
    0.07
     collapsing
    0.07
    -transform
    0.07
     wallets
    0.07
     �
    0.07
    า�
    0.07
     пода
    0.07
     ED
    0.06
     цик
    0.06
    Act Density 0.006%

    No Known Activations