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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Nó
    0.85
     Univer
    0.78
     челове
    0.75
    espół
    0.75
     Mankind
    0.74
     Gemini
    0.73
     Muscle
    0.72
     Casualty
    0.71
     Breakdown
    0.70
     Muskel
    0.70
    POSITIVE LOGITS
     whose
    0.66
     moeilijk
    0.65
    情報の
    0.64
    傻
    0.64
    輛
    0.63
    がいる
    0.62
    requires
    0.61
     carcasses
    0.61
     moored
    0.61
     prévenir
    0.61
    Act Density 0.910%

    No Known Activations