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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     absorbed
    -0.07
    发现
    -0.07
     Via
    -0.06
    =(-
    -0.06
     packets
    -0.06
     од
    -0.06
    沖
    -0.06
    à
    -0.06
     fruit
    -0.06
    (proxy
    -0.06
    POSITIVE LOGITS
     []);↵↵
    0.07
    .getDay
    0.06
    >({↵
    0.06
    	hs
    0.06
    なが
    0.06
    -place
    0.06
     Nationwide
    0.06
     गई
    0.06
    .'),↵
    0.06
    Disappear
    0.06
    Act Density 0.526%

    No Known Activations