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

    Neuronpedia

    INDEX
    Explanations

    argued

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     battalion
    -0.08
    (Product
    -0.07
    versions
    -0.07
     login
    -0.07
    THREAD
    -0.07
     wash
    -0.07
     fld
    -0.07
    wash
    -0.06
    ков
    -0.06
     Molecular
    -0.06
    POSITIVE LOGITS
    )throws
    0.07
    /");↵
    0.07
    	throws
    0.06
     argued
    0.06
    ++)↵
    0.06
    alling
    0.06
     соот
    0.06
     unexpected
    0.06
    '},
↵
    0.06
    0.06
    Act Density 0.001%

    No Known Activations