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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    抹茶
    0.52
    綺麗な
    0.46
     sacrificed
    0.45
     sacrific
    0.43
    ತಕ್ಕ
    0.42
     productor
    0.42
     menang
    0.42
     круг
    0.41
     sacrifice
    0.41
     tercer
    0.41
    POSITIVE LOGITS
    Imper
    0.46
     Populate
    0.43
    விடும்
    0.40
     Imper
    0.40
     sql
    0.39
    oles
    0.39
     শত্রু
    0.38
    akespe
    0.37
    igon
    0.37
    читать
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.