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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dot
    -0.08
     tower
    -0.07
     overt
    -0.07
    olithic
    -0.07
     Roger
    -0.07
     poisoned
    -0.07
    .published
    -0.07
    Layer
    -0.06
    	order
    -0.06
     Bieber
    -0.06
    POSITIVE LOGITS
    )o
    0.06
    882
    0.06
    %'↵
    0.06
    织
    0.05
    _MODULE
    0.05
     ‎
    0.05
    ..
    0.05
    uguay
    0.05
    Iterator
    0.05
    รร
    0.05
    Act Density 0.007%

    No Known Activations