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

    Neuronpedia

    INDEX
    Explanations

    states of being, qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     успешно
    0.78
     अत्य
    0.74
    optimized
    0.73
    optimize
    0.70
     Optimized
    0.69
    ensibly
    0.68
     correctamente
    0.68
     monopolist
    0.66
    blob
    0.66
     Essentially
    0.66
    POSITIVE LOGITS
     contagious
    0.95
     worth
    0.94
     worthwhile
    0.92
     valid
    0.86
     palpable
    0.83
     important
    0.82
     meaningful
    0.81
     yours
    0.81
     sincere
    0.81
     magnified
    0.79
    Act Density 0.923%

    No Known Activations