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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝓪
    1.05
    на
    1.02
    ни
    0.98
     nombreuses
    0.86
    𝓸
    0.84
    oarece
    0.84
     необхід
    0.84
     liés
    0.84
    일
    0.84
    SKA
    0.82
    POSITIVE LOGITS
     one
    0.78
     dined
    0.75
     was
    0.72
    time
    0.72
     elections
    0.71
     reality
    0.71
     weighing
    0.71
     negotiation
    0.71
     election
    0.70
     world
    0.70
    Act Density 0.005%

    No Known Activations