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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     +=
    -0.08
    [r
    -0.07
     ()=>{↵
    -0.07
    崴
    -0.07
    ⯈
    -0.07
    เทศ
    -0.07
     bombings
    -0.06
     nye
    -0.06
    ♁
    -0.06
    ሲ
    -0.06
    POSITIVE LOGITS
     Herald
    0.08
    散热
    0.08
     neighbour
    0.07
     הנוכ
    0.07
     electrodes
    0.07
    keys
    0.07
    Sequential
    0.07
    Cell
    0.07
    知识分子
    0.07
     substitution
    0.07
    Act Density 0.006%

    No Known Activations