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

    Neuronpedia

    INDEX
    Explanations

    NSURL

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]]:↵
    -0.08
    .awt
    -0.07
     VAN
    -0.07
    #================================================================
    -0.07
    >();↵↵
    -0.07
    (po
    -0.07
     pharmac
    -0.06
    奧
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.06
     ac
    -0.06
    POSITIVE LOGITS
    桢
    0.07
    干线
    0.07
     ugl
    0.07
     On
    0.07
    满分
    0.07
    ancell
    0.07
    钧
    0.06
     juni
    0.06
    _MALLOC
    0.06
     plugin
    0.06
    Act Density 0.002%

    No Known Activations