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

    Neuronpedia

    INDEX
    Explanations

    Excerpts from documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coolant
    -0.07
    riger
    -0.07
     Notice
    -0.06
     looming
    -0.06
     Doug
    -0.06
     Sitting
    -0.06
    txt
    -0.06
     spiele
    -0.06
    damn
    -0.06
     acquiring
    -0.06
    POSITIVE LOGITS
    ]?
    0.07
    ?
    0.07
     }↵
    0.07
     subscribers
    0.07
    ]:↵↵
    0.07
     })
↵
↵
    0.07
    ！！
    0.07
    '}).
    0.07
     */↵↵↵↵
    0.06
    )):
↵
    0.06
    Act Density 0.001%

    No Known Activations