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

    Neuronpedia

    INDEX
    Explanations

    Snippets of larger texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Characteristics
    -0.07
     ERC
    -0.06
     accessibility
    -0.06
    Repositories
    -0.06
    ：“
    -0.06
     ****************************************************************
    -0.06
    ened
    -0.06
    ，“
    -0.06
    selector
    -0.05
    Clusters
    -0.05
    POSITIVE LOGITS
    )]
↵
    0.07
    ี้↵
    0.07
    ]');↵
    0.07
     ]);↵
    0.07
    "=>
    0.07
     sessiz
    0.07
    .std
    0.07
    }})↵
    0.07
     assertThat
    0.06
    ]))
↵
    0.06
    Act Density 0.233%

    No Known Activations