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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    direction
    0.40
    notin
    0.40
    shi
    0.40
    दूर
    0.40
    urato
    0.39
    m
    0.39
    ］
    0.39
     clara
    0.38
    k
    0.38
    paragraph
    0.38
    POSITIVE LOGITS
     库存
    0.46
    BatchNorm
    0.45
    ICKET
    0.45
     نر
    0.44
    టర్
    0.44
    DESCRIPTION
    0.44
    వ్
    0.44
    িনবার্গ
    0.43
    YNAMICS
    0.43
     设计
    0.42
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.