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

    Neuronpedia

    INDEX
    Explanations

    ?)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interpolate
    -0.07
     Voting
    -0.06
     inoc
    -0.06
    olding
    -0.06
    asily
    -0.06
    'ét
    -0.06
     liners
    -0.06
     increases
    -0.06
    	stack
    -0.06
     cloning
    -0.06
    POSITIVE LOGITS
    ?)
    0.26
    ?),
    0.16
    ?).
    0.15
     (?)
    0.14
    ?)↵
    0.13
    ?)↵↵
    0.11
    ?]
    0.10
    ?):
    0.09
    !]
    0.09
    .VideoCapture
    0.08
    Act Density 0.006%

    No Known Activations