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

    Neuronpedia

    INDEX
    Explanations

    irical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iddled
    -0.08
    	grid
    -0.08
    Rot
    -0.07
    =row
    -0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.07
    >>>>
    -0.07
     Rotation
    -0.06
     adoles
    -0.06
    ded
    -0.06
     sep
    -0.06
    POSITIVE LOGITS
     empirical
    0.09
     empir
    0.08
    402
    0.07
    (bodyParser
    0.06
    Battery
    0.06
    '>
↵
    0.06
     Simpson
    0.06
     employers
    0.06
    irical
    0.06
     recourse
    0.06
    Act Density 0.004%

    No Known Activations