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

    Neuronpedia

    INDEX
    Explanations

    each other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     combinatie
    0.87
     combination
    0.81
     grouping
    0.76
     associated
    0.75
     tutte
    0.74
    Two
    0.73
     Kết
    0.73
     combinación
    0.72
     combining
    0.72
    }+\
    0.72
    POSITIVE LOGITS
    对方
    0.78
    對方
    0.71
     друг
    0.67
    하나
    0.63
     wards
    0.63
     البعض
    0.61
     influences
    0.61
     прости
    0.60
    quina
    0.59
    व्
    0.59
    Act Density 0.078%

    No Known Activations