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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     on
    0.47
     yield
    0.44
    只会
    0.41
     get
    0.40
     c
    0.38
     updateConfirm
    0.38
     study
    0.38
     গ্রেপ্ত
    0.38
     recruits
    0.37
     sequences
    0.37
    POSITIVE LOGITS
     स्वतंत्र
    0.52
    𝘃
    0.51
    стрии
    0.48
    ransport
    0.47
     πολλ
    0.46
    मता
    0.46
    <unused278>
    0.46
    laublich
    0.46
     छोटे
    0.45
    <unused2023>
    0.45
    Act Density 0.015%

    No Known Activations