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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ES
    0.52
    ्यूट
    0.51
     আধুনিক
    0.48
    ET
    0.47
    ts
    0.45
    ety
    0.45
    gui
    0.45
    onu
    0.44
    TS
    0.43
    Bach
    0.43
    POSITIVE LOGITS
    濃度
    0.48
     helt
    0.46
     działa
    0.46
     Jaff
    0.46
    μφωνα
    0.43
    spraak
    0.42
    columnwidth
    0.42
    ίναι
    0.41
    واره
    0.41
     många
    0.41
    Act Density 0.008%

    No Known Activations