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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     സാഹചര്യ
    -0.08
     благодаря
    -0.08
    hela
    -0.07
     Bahn
    -0.07
    ogn
    -0.07
     PHY
    -0.07
    ẩm
    -0.07
     Toyota
    -0.07
     tunnet
    -0.07
     luncheon
    -0.07
    POSITIVE LOGITS
     verzichten
    0.10
     reluctantly
    0.09
     HOWEVER
    0.09
     alsnog
    0.09
    /public
    0.08
     intentar
    0.08
    免责
    0.08
    plier
    0.08
     instead
    0.08
    �
    0.08
    Act Density 0.041%

    No Known Activations