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

    Neuronpedia

    INDEX
    Explanations

    Code snippets, documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tactics
    -0.07
    よび
    -0.06
     кому
    -0.06
     Faction
    -0.06
    compressed
    -0.06
     incontro
    -0.06
     останов
    -0.06
    (pack
    -0.06
     매우
    -0.05
    -es
    -0.05
    POSITIVE LOGITS
    .ย
    0.07
    >↵↵↵
    0.07
    earer
    0.07
    480
    0.06
     refining
    0.06
     Brendan
    0.06
     QtGui
    0.06
    ी।↵
    0.06
    ()}↵
    0.06
    FILENAME
    0.06
    Act Density 0.023%

    No Known Activations