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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     troub
    -0.07
     �
    -0.07
     ghé
    -0.07
     노
    -0.07
     RSVP
    -0.07
     למנ
    -0.07
    AllowAnonymous
    -0.07
     redistributed
    -0.07
     guarded
    -0.07
     testers
    -0.07
    POSITIVE LOGITS
    iram
    0.07
    upil
    0.07
    feat
    0.06
     '".
    0.06
    工艺品
    0.06
    .rect
    0.06
    apt
    0.06
    我が家
    0.06
    海口
    0.06
    我家
    0.06
    Act Density 0.003%

    No Known Activations