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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     chiến
    0.36
    เพื่อน
    0.34
     khiến
    0.34
     możesz
    0.34
    ̓
    0.34
     puoi
    0.33
     nedenle
    0.33
     א
    0.32
     marito
    0.32
     erbjuder
    0.32
    POSITIVE LOGITS
    ओएस
    0.43
    ubine
    0.40
    ુ
    0.38
     deformity
    0.37
    ult
    0.37
    ığın
    0.37
    izquierda
    0.36
    found
    0.36
    یشہ
    0.36
    not
    0.35
    Act Density 0.000%

    No Known Activations