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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    נייר
    -0.08
    אוג
    -0.08
    صحاب
    -0.07
    煳
    -0.07
    滘
    -0.07
    ῷ
    -0.07
     AAC
    -0.06
    modifiers
    -0.06
    ユー
    -0.06
    供热
    -0.06
    POSITIVE LOGITS
    /"
    0.07
    pm
    0.07
    盤
    0.07
     staring
    0.07
     قامت
    0.07
     Gl
    0.07
    玤
    0.06
    ::{
    0.06
    標準
    0.06
     official
    0.06
    Act Density 0.004%

    No Known Activations