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

    Neuronpedia

    INDEX
    Explanations

    classified as inferior or objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    琯
    0.43
     Quir
    0.41
     ప్రతి
    0.40
     disapproval
    0.40
     conventionally
    0.39
     overshadow
    0.39
     Richter
    0.38
    􀂾
    0.37
    丕
    0.37
    传统的
    0.37
    POSITIVE LOGITS
     inferior
    0.93
     worthless
    0.88
     inferiores
    0.88
     inférieurs
    0.83
     verm
    0.82
     inférieure
    0.80
    infer
    0.79
     inferiore
    0.77
     inférieures
    0.77
     inférieur
    0.75
    Act Density 0.025%

    No Known Activations