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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     derel
    0.71
     negligence
    0.68
     prosecution
    0.68
    ounds
    0.67
    negl
    0.65
     tenderness
    0.65
     neglig
    0.64
    olition
    0.63
     pulses
    0.63
    %]
    0.63
    POSITIVE LOGITS
     strategi
    0.81
     Anpass
    0.81
     memutuskan
    0.78
     modificare
    0.77
     introduced
    0.77
    🗓
    0.75
    限
    0.75
    <0xB1>
    0.74
     Adjustment
    0.74
    创建
    0.72
    Act Density 0.031%

    No Known Activations