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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝚒
    0.37
    𝚗
    0.34
    𝚐
    0.34
    𝚋
    0.32
    𝚜
    0.32
    Kill
    0.31
    Remove
    0.31
     Stripes
    0.31
    Removal
    0.31
    Proveedor
    0.30
    POSITIVE LOGITS
     zakres
    0.38
     correlated
    0.37
     thoracique
    0.37
     посмотрим
    0.35
     autocorrelation
    0.35
    ν
    0.35
    rine
    0.34
     изучение
    0.33
     אחר
    0.33
     eviden
    0.33
    Act Density 0.913%

    No Known Activations