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

    Neuronpedia

    INDEX
    Explanations

    study names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ordes
    -0.08
    坪
    -0.07
    urgence
    -0.07
    uncia
    -0.07
    atrix
    -0.07
    ACKET
    -0.06
     cynical
    -0.06
    ベン
    -0.06
     đóng
    -0.06
     Kosovo
    -0.06
    POSITIVE LOGITS
     circulated
    0.07
    .serialization
    0.07
    >-->↵
    0.07
     �
    0.06
    حوال
    0.06
    ייעוץ
    0.06
    		
↵
    0.06
    �
    0.06
     accumulated
    0.06
    ▓
    0.06
    Act Density 0.033%

    No Known Activations