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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     �
    -0.06
     Deng
    -0.06
    .orientation
    -0.06
    (m
    -0.06
    [m
    -0.06
     wounded
    -0.06
     FloatingActionButton
    -0.06
     gol
    -0.06
     lep
    -0.06
    POSITIVE LOGITS
    额
    0.07
    RIPTION
    0.07
     numero
    0.07
    "d
    0.07
    implement
    0.07
    %.↵
    0.07
     demonstrating
    0.06
    лава
    0.06
    ія
    0.06
    مع
    0.06
    Act Density 0.000%

    No Known Activations